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

    Neuronpedia

    INDEX
    Explanations

    post-dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ris
    0.46
    rista
    0.45
    formed
    0.44
    InitFlag
    0.44
     precludes
    0.43
    ’
    0.42
     /*
    0.41
     svom
    0.41
     LANGUAGE
    0.40
    red
    0.40
    POSITIVE LOGITS
    ب
    0.56
    س
    0.52
    ス
    0.50
    спи
    0.50
    idł
    0.48
    мени
    0.48
     керек
    0.46
     лига
    0.45
    они
    0.44
    اشی
    0.44
    Act Density 0.001%

    No Known Activations