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

    Neuronpedia

    INDEX
    Explanations

    noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    1.10
     I
    0.98
    s
    0.96
     (
    0.93
     For
    0.92
    i
    0.88
     If
    0.86
    don
    0.83
     Neurology
    0.82
    for
    0.81
    POSITIVE LOGITS
    사
    1.13
     as
    1.10
    ため
    1.10
    的
    1.05
    가
    1.04
    ا
    0.98
    지만
    0.97
    يد
    0.95
    ル
    0.93
    스를
    0.93
    Act Density 0.000%

    No Known Activations