Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    from sklearn imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asyncio
    0.52
     traceback
    0.46
     monotonic
    0.44
     streamlit
    0.42
     bibliographic
    0.42
     bosonic
    0.42
     python
    0.41
     pajama
    0.41
     библиоте
    0.40
     library
    0.40
    POSITIVE LOGITS
    Matthew
    0.59
     Matthew
    0.52
    sk
    0.51
     sklearn
    0.49
     SK
    0.47
    Sk
    0.47
     Statistik
    0.46
    SK
    0.46
     مط
    0.46
     স্ক
    0.46
    Act Density 0.008%

    No Known Activations