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

    Neuronpedia

    INDEX
    Explanations

    class MainActivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forest
    0.41
    caps
    0.40
    '
    0.39
    ^{-/-}$
    0.39
    heard
    0.39
    pieceSelection
    0.38
    पृथ्वी
    0.38
    䜣
    0.38
    unavailable
    0.38
    älter
    0.38
    POSITIVE LOGITS
     ۱
    0.43
     درجہ
    0.42
     porcentaje
    0.41
     Jumlah
    0.41
     ۵
    0.41
     سبسڈی
    0.41
     Produtos
    0.40
     consegna
    0.40
     ۸
    0.39
     seguintes
    0.39
    Act Density 0.001%

    No Known Activations