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

    Neuronpedia

    INDEX
    Explanations

    perspective and perspective shift

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺩ
    1.95
     terribly
    1.94
    ت
    1.91
    போதும்
    1.84
    ע
    1.80
    ない
    1.80
    웨어
    1.79
    梆
    1.78
    IO
    1.76
    IFT
    1.76
    POSITIVE LOGITS
    ff
    2.13
    ção
    1.95
     Öffentlichkeit
    1.94
    c
    1.85
    ž
    1.73
     Nähe
    1.63
    bentuk
    1.57
    utiva
    1.57
    ónimo
    1.56
    zza
    1.55
    Act Density 0.018%

    No Known Activations