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

    Neuronpedia

    INDEX
    Explanations

    institutions, places, and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    -2.08
    As
    -1.71
    U
    -1.69
    ;
    -1.67
    A
    -1.57
    j
    -1.52
    s
    -1.52
    P
    -1.51
    S
    -1.51
    u
    -1.51
    POSITIVE LOGITS
    ジナル
    1.83
    Waga
    1.61
     granito
    1.55
    虓
    1.52
    してました
    1.52
    內容簡介
    1.50
     Pastikan
    1.47
    Tempat
    1.46
    zapatillas
    1.46
    Warna
    1.45
    Act Density 0.000%

    No Known Activations