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

    Neuronpedia

    INDEX
    Explanations

    IEEE technical papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.83
    راب
    0.76
    $
    0.75
    ﺲ
    0.75
    ે
    0.72
    getCQL
    0.71
    ian
    0.70
    ја
    0.69
    á
    0.68
    ier
    0.68
    POSITIVE LOGITS
    IS
    0.89
    ש
    0.88
    هم
    0.81
    Ро
    0.77
    On
    0.75
     Disable
    0.75
    Об
    0.74
     Initialize
    0.73
    vať
    0.73
    an
    0.73
    Act Density 0.001%

    No Known Activations