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

    Neuronpedia

    INDEX
    Explanations

    feudalism and capitalism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鳧
    0.55
    ص
    0.52
    ა
    0.51
    PathVariable
    0.49
    ಅ
    0.48
    awan
    0.48
    ͢
    0.48
    geräte
    0.48
    тись
    0.47
     comedian
    0.47
    POSITIVE LOGITS
     className
    0.43
    儡
    0.41
    ಾರಂಭ
    0.41
     vies
    0.41
     magn
    0.40
    (`<
    0.39
    -\{
    0.39
    Зна
    0.39
    ized
    0.39
    ueur
    0.39
    Act Density 0.026%

    No Known Activations