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

    Neuronpedia

    INDEX
    Explanations

    code punctuation followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pontos
    0.94
     попы
    0.92
     игровой
    0.92
     получение
    0.91
     kov
    0.91
     гидро
    0.90
     fhe
    0.89
     учетом
    0.87
     sáb
    0.87
     IRB
    0.87
    POSITIVE LOGITS
    ı
    0.90
    IV
    0.89
    :
    0.87
    Pag
    0.84
    投资基金
    0.84
    Pap
    0.79
    Expr
    0.78
    봐
    0.78
     flagship
    0.77
    Por
    0.77
    Act Density 0.001%

    No Known Activations