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

    Neuronpedia

    INDEX
    Explanations

    int main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lorsque
    0.52
     acceleration
    0.49
    Cuando
    0.48
    Quando
    0.44
     sayısı
    0.44
     "--
    0.43
     cuando
    0.42
    速度
    0.42
    '
    0.42
    When
    0.42
    POSITIVE LOGITS
     ㅅ
    0.53
    mu
    0.51
     mub
    0.47
     mu
    0.44
     munc
    0.42
    dut
    0.42
     Giac
    0.41
     Ss
    0.40
    ty
    0.40
     cinc
    0.40
    Act Density 0.008%

    No Known Activations