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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibilidad
    -0.07
     faux
    -0.07
     Deep
    -0.07
     nal
    -0.07
    grams
    -0.06
    ارات
    -0.06
    ODY
    -0.06
    grid
    -0.06
     đốc
    -0.06
     patio
    -0.06
    POSITIVE LOGITS
    $IFn
    0.07
    .pkl
    0.07
    (++
    0.06
    เย
    0.06
     тяж
    0.06
     وك
    0.06
    .entities
    0.06
     нег
    0.06
    تبه
    0.06
    (quantity
    0.06
    Act Density 0.000%

    No Known Activations