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

    Neuronpedia

    INDEX
    Explanations

    imposing will or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    は
    1.18
    是
    1.09
    ту
    1.01
    ен
    0.97
    는
    0.95
    но
    0.93
     as
    0.91
    ме
    0.89
    ли
    0.88
    لا
    0.88
    POSITIVE LOGITS
    م
    1.12
    ம்
    0.98
    ’
    0.86
    it
    0.84
     imposition
    0.83
     lancement
    0.82
    ना
    0.82
    pc
    0.80
    й
    0.80
    지
    0.79
    Act Density 0.008%

    No Known Activations