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

    Neuronpedia

    INDEX
    Explanations

    bright smile, confidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    0.80
    ι
    0.70
    家
    0.70
    ol
    0.70
    نا
    0.66
    ip
    0.64
    し
    0.63
    ونية
    0.61
    ام
    0.60
    ুর
    0.60
    POSITIVE LOGITS
    0
    0.80
     bebas
    0.66
     exiled
    0.64
     americ
    0.63
     you
    0.62
    zelf
    0.61
     novoProduto
    0.60
     виправи
    0.59
     엔진
    0.59
     amerikan
    0.59
    Act Density 0.001%

    No Known Activations