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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cak
    -0.08
    �
    -0.07
    seh
    -0.07
     Flint
    -0.07
    😉
    -0.07
    z
    -0.07
     सं
    -0.07
    zio
    -0.07
     aud
    -0.07
    ook
    -0.07
    POSITIVE LOGITS
     мужч
    0.09
     приходит
    0.09
    ისწ
    0.09
     Dud
    0.09
     வந்த
    0.09
     მამ
    0.09
     Reino
    0.08
     мужчина
    0.08
     قانون
    0.08
    -----------------------------------------------------------------------------↵
    0.08
    Act Density 0.008%

    No Known Activations