PAIR-code/lit
The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.
This tool helps machine learning engineers and researchers understand how their ML models behave. You input your model (supporting text, image, or tabular data) and relevant datasets, and it outputs interactive visualizations and analyses in a web browser. This allows you to explore model predictions, identify errors, and debug performance issues.
3,640 stars.
Use this if you need to visually and interactively analyze why your machine learning model makes specific predictions or where it performs poorly.
Not ideal if you're looking for an automated model optimization solution or a tool for general data exploration unrelated to ML model behavior.
Stars
3,640
Forks
371
Language
TypeScript
License
Apache-2.0
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PAIR-code/lit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...