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

    Neuronpedia

    INDEX
    Explanations

    import code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    భవ
    0.72
    fts
    0.70
    prex
    0.69
     domen
    0.67
     domeni
    0.67
    umab
    0.66
    domain
    0.66
     doh
    0.65
     sap
    0.65
    isna
    0.64
    POSITIVE LOGITS
     liegen
    0.72
     масштаб
    0.69
    횡
    0.68
     schreiben
    0.65
    Gravity
    0.64
    TempValue
    0.62
     считать
    0.62
    ucionales
    0.61
     motions
    0.61
    selValue
    0.60
    Act Density 0.000%

    No Known Activations