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

    Neuronpedia

    INDEX
    Explanations

    mixed, unrelated texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NSS
    -0.08
    finite
    -0.07
    zap
    -0.07
    beat
    -0.07
    ость
    -0.07
    Sum
    -0.07
    ZO
    -0.07
     Baldwin
    -0.06
    wise
    -0.06
    Crow
    -0.06
    POSITIVE LOGITS
    licence
    0.06
     Pinterest
    0.06
    {o
    0.06
     pricing
    0.06
     NGOs
    0.06
    [column
    0.06
    hl
    0.06
     Dennis
    0.06
     deren
    0.05
    [ch
    0.05
    Act Density 0.000%

    No Known Activations