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

    Neuronpedia

    INDEX
    Explanations

    find specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.81
    ري
    0.79
    يز
    0.77
    يو
    0.75
    ربي
    0.74
    <0x0D>
    0.73
    ليل
    0.72
    но
    0.71
    ويات
    0.71
    ことで
    0.69
    POSITIVE LOGITS
    in
    1.18
    ת
    0.91
    א
    0.89
    ある
    0.88
    ל
    0.87
     find
    0.86
    ა
    0.84
    した
    0.84
    yı
    0.82
    '
    0.82
    Act Density 0.238%

    No Known Activations