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

    Neuronpedia

    INDEX
    Explanations

    documentation enders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inorganic
    0.90
     Silicon
    0.86
     inorganic
    0.84
     Electronic
    0.83
     digital
    0.82
     hardworking
    0.81
     onboarding
    0.80
     titular
    0.80
     KPIs
    0.79
    精密
    0.79
    POSITIVE LOGITS
    参见
    1.04
    see
    1.03
    See
    0.97
     see
    0.91
    詳しくは
    0.86
    ToRemove
    0.84
     See
    0.81
    別途
    0.80
     مگر
    0.80
     tuttavia
    0.79
    Act Density 0.451%

    No Known Activations