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

    Neuronpedia

    INDEX
    Explanations

    Q: Indian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    -2.02
    1
    -1.77
    мся
    -1.69
     gewüns
    -1.66
    ING
    -1.62
    \
    -1.62
     []:
    -1.61
     gleiche
    -1.55
     To
    -1.55
     Gründe
    -1.55
    POSITIVE LOGITS
     successes
    1.80
     now
    1.77
    迺
    1.69
    Ꮉ
    1.66
    afari
    1.66
    ᴎ
    1.65
    that
    1.63
    鋱
    1.63
     сейчас
    1.61
     ),
    1.61
    Act Density 0.000%

    No Known Activations