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

    Neuronpedia

    INDEX
    Explanations

    pluralizing nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconven
    0.45
     efficiently
    0.40
    将会
    0.39
    NUMX
    0.39
     industrious
    0.39
    すべての
    0.38
    无论
    0.38
    諾
    0.38
     навіть
    0.38
     respectively
    0.37
    POSITIVE LOGITS
    pseudo
    0.41
     بازار
    0.40
     pembayaran
    0.39
     Angaben
    0.39
    pony
    0.39
     seiner
    0.39
    TextBox
    0.38
    Placement
    0.38
     చేసింది
    0.38
     இருந்தார்
    0.38
    Act Density 0.014%

    No Known Activations