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

    Neuronpedia

    INDEX
    Explanations

    log

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    衣
    0.96
    ![](
    0.93
    팅
    0.91
     nodded
    0.91
    URDAY
    0.91
    oubliez
    0.91
    larger
    0.90
    ty
    0.89
    filterable
    0.87
     nullable
    0.87
    POSITIVE LOGITS
    arithmic
    2.14
    istical
    1.81
    arith
    1.73
    arit
    1.55
    istics
    1.54
    gings
    1.53
    輯
    1.41
    ်
    1.33
    gers
    1.32
     arrhyth
    1.28
    Act Density 0.086%

    No Known Activations