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

    Neuronpedia

    INDEX
    Explanations

    time zone abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.66
    et
    0.63
    ть
    0.53
     grandeur
    0.52
    ς
    0.50
    ak
    0.49
    a
    0.48
    ;
    0.48
    ուն
    0.48
    as
    0.47
    POSITIVE LOGITS
     الاجتما
    0.55
    lä
    0.50
    お
    0.50
     These
    0.49
     Cré
    0.49
    ول
    0.49
    ۔
    0.48
    时间
    0.48
    تج
    0.48
     काउंसिल
    0.47
    Act Density 0.000%

    No Known Activations