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

    Neuronpedia

    INDEX
    Explanations

    prime factorization and division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    白
    0.43
    绑
    0.37
    ushchev
    0.37
    影
    0.36
    轻
    0.35
    shims
    0.34
     লিখিত
    0.34
    室
    0.33
    uture
    0.33
    流
    0.33
    POSITIVE LOGITS
     заказа
    0.43
     zum
    0.43
     certific
    0.43
     seleccionado
    0.42
     handelt
    0.41
     sporty
    0.41
    Peru
    0.41
    夭
    0.40
    mozilla
    0.40
     costes
    0.40
    Act Density 0.005%

    No Known Activations