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

    Neuronpedia

    INDEX
    Explanations

    for _, variable range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )(
    0.45
     ganze
    0.41
     moe
    0.39
     Processing
    0.39
     individ
    0.38
     (
    0.38
     obsol
    0.38
    (
    0.37
     обрабо
    0.37
     lipids
    0.37
    POSITIVE LOGITS
     _,
    0.78
     —,
    0.77
     -,
    0.68
     –,
    0.68
    --,
    0.65
     ---
    0.62
    __,
    0.57
     ------
    0.57
    _,
    0.56
    $-$,
    0.55
    Act Density 0.000%

    No Known Activations