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

    Neuronpedia

    INDEX
    Explanations

    start of html documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    辫
    0.72
    stery
    0.72
     atof
    0.71
    }/>
    0.70
     tino
    0.69
    iyê
    0.68
     fint
    0.68
     উদ্বাস্তুদের
    0.68
    iena
    0.68
     vorhand
    0.68
    POSITIVE LOGITS
    html
    0.90
    <html>
    0.75
    htm
    0.75
     html
    0.73
    ht
    0.64
    lang
    0.60
    modelVersion
    0.57
    index
    0.57
    <?
    0.56
    public
    0.56
    Act Density 0.125%

    No Known Activations