kanishkamisra/minicons

Utility for behavioral and representational analyses of Language Models

67
/ 100
Established

This project helps researchers and scientists understand how large language models (LLMs) process language and make predictions. It allows you to input text and images to extract numerical representations of words or to calculate how 'surprising' a word or sentence is to a model. The output helps analyze the internal workings and biases of LLMs, making it useful for computational linguists, cognitive scientists, or anyone evaluating AI language behavior.

183 stars. Used by 1 other package. Available on PyPI.

Use this if you need to systematically analyze the behavioral and representational properties of various language models, including how they score text sequences or process visual information alongside text.

Not ideal if you are looking for a tool to train new language models or to perform general-purpose natural language processing tasks like text classification or sentiment analysis.

computational-linguistics cognitive-science ai-ethics language-model-analysis nlp-research
Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

183

Forks

41

Language

Python

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

9

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kanishkamisra/minicons"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.