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

    Neuronpedia

    INDEX
    Explanations

    package com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dens
    0.85
    ita
    0.79
    itos
    0.79
    news
    0.78
    Adult
    0.78
    adult
    0.77
    copies
    0.77
    donor
    0.75
    do
    0.74
    normalize
    0.74
    POSITIVE LOGITS
     fontFamily
    0.89
     FontFamily
    0.86
     middleware
    0.84
     com
    0.84
     trimester
    0.82
     edu
    0.80
     IntegerValue
    0.79
    日內
    0.78
     स्कैनर
    0.78
     fierce
    0.77
    Act Density 0.013%

    No Known Activations