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

    Neuronpedia

    INDEX
    Explanations

    novel reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خ
    0.81
     Кон
    0.80
     Раз
    0.78
     Това
    0.77
     Сен
    0.77
     терито
    0.75
    Nuestro
    0.75
     типо
    0.73
     метра
    0.72
     Центра
    0.71
    POSITIVE LOGITS
     tệ
    0.86
     daughters
    0.85
     worsened
    0.82
     cuja
    0.82
     jogos
    0.81
     worsen
    0.81
     biển
    0.80
    所謂
    0.79
     siquiera
    0.77
     teljesen
    0.77
    Act Density 0.000%

    No Known Activations