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

    Neuronpedia

    INDEX
    Explanations

    overall summary average date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.06
    1.04
    0.91
    0.84
    -​
    0.80
     belliger
    0.79
    ‑
    0.78
     imperatives
    0.77
    usepackage
    0.76
     сказал
    0.75
    POSITIVE LOGITS
    total
    0.86
    2
    0.86
    corsi
    0.85
    cji
    0.82
    6
    0.82
    horas
    0.82
    1
    0.82
    셜
    0.78
    而言
    0.78
    टर
    0.77
    Act Density 0.398%

    No Known Activations