Learning Interpretability Tool (LIT)

JSON →
library 1.3.1 ·python
verified Apr 27, 2026

LIT (Learning Interpretability Tool) is an open-source platform from PAIR (People + AI Research) at Google for visualizing and understanding machine learning models. Version 1.3.1 supports interpretability of generative AI, including sequence salience for LLMs, and can be deployed on Google Cloud with public container images. Releases occur approximately every 6 months.

total hits 14
actors 6 distinct systems
last hit 6d ago human
MetaBot
3
GPTBot
2
Script
1
Search engines
1
Humans
2

top countries 🇺🇸 United States · 🇨🇦 Canada · 🇫🇷 France · 🇩🇪 Germany · 🇮🇳 India