# LIT

> Learning Interpretability Tool: interactive visual analysis of ML model behavior, by Google PAIR.

- Category: [Machine learning visualization tools](https://awesomedataviz.com/categories/machine-learning/)
- Website: https://pair-code.github.io/lit
- Repository: https://github.com/PAIR-code/lit
- License: Apache-2.0
- Language: TypeScript
- Status: Inactive (no commits in over a year)
- GitHub stars: 3,668
- Commits in the last 12 months: 0
- Contributors: 37
- Last commit: Dec 20, 2024
- Latest release: v1.3.1 (Dec 20, 2024)
- Install (PyPI): `pip install lit-nlp`, 1.3K downloads per week
- Topics: Machine learning & AI visualization

## Overview

LIT is an open-source ML visualization tool released under the Apache-2.0 license. Its GitHub repository has 3,668 stars, 366 forks, and 37 contributors. It has not had a commit since Dec 20, 2024. The latest release, v1.3.1, was published on Dec 20, 2024. On PyPI it is downloaded about 1.3K times per week.

## Alternatives

- [Netron](https://awesomedataviz.com/tools/netron/): Viewer for neural network, deep learning and machine learning models. (33.5K stars)
- [PlotNeuralNet](https://awesomedataviz.com/tools/plotneuralnet/): LaTeX code for drawing neural network architecture diagrams. (25K stars)
- [Opik](https://awesomedataviz.com/tools/opik/): Formerly CometLLM. Debug, evaluate, and monitor LLM applications with tracing and dashboards. (22.4K stars)
- [Phoenix](https://awesomedataviz.com/tools/phoenix/): ML observability in a notebook with UMAP visualizations (11.7K stars)
- [FiftyOne](https://awesomedataviz.com/tools/fiftyone/): Tool for visualizing, curating and evaluating computer vision datasets and models. (11.1K stars)
- [Visdom](https://awesomedataviz.com/tools/visdom/): Tool for real-time visualization and monitoring of live data such as ML experiments. (10.3K stars)

Source: https://awesomedataviz.com/tools/lit/ · Data updated 2026-10-04 · Content: CC BY 4.0, Awesome Dataviz (https://awesomedataviz.com).