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

    Neuronpedia

    INDEX
    Explanations

    separating list items with commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.09
    in
    0.90
    k
    0.88
    ش
    0.88
     (
    0.82
     A
    0.82
    a
    0.77
     H
    0.74
     R
    0.73
    了他的
    0.72
    POSITIVE LOGITS
    ות
    1.05
    ви
    0.93
    })$.
    0.93
    تين
    0.87
    <0x80>
    0.86
    ва
    0.83
    вого
    0.82
    ган
    0.81
    ಭ
    0.79
    вается
    0.78
    Act Density 0.027%

    No Known Activations