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

    Neuronpedia

    INDEX
    Explanations

    all the way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘃
    0.77
    ও
    0.77
     escuch
    0.76
    കാല
    0.73
     cortar
    0.72
    жа
    0.71
    면
    0.70
    čku
    0.68
     a
    0.67
     yönelik
    0.67
    POSITIVE LOGITS
    ر
    1.09
    are
    0.79
    re
    0.73
    ス
    0.72
     угодно
    0.71
    ä
    0.71
    le
    0.69
     ر
    0.68
     Atwood
    0.68
    ان
    0.67
    Act Density 0.003%

    No Known Activations