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

    Neuronpedia

    INDEX
    Explanations

    model html love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    轼
    0.67
    Basel
    0.63
    тивную
    0.57
     scoped
    0.57
    bellum
    0.56
    ibas
    0.55
     scol
    0.55
    deliver
    0.55
    icylic
    0.54
    тивного
    0.54
    POSITIVE LOGITS
     نمی
    0.59
     مک
    0.56
    フォード
    0.55
     Gods
    0.54
     ве
    0.54
     ف
    0.54
    际
    0.54
     ভূ
    0.54
     Selbst
    0.53
    anía
    0.53
    Act Density 0.267%

    No Known Activations