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

    Neuronpedia

    INDEX
    Explanations

    mod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attrs
    -0.06
    (":/
    -0.06
     پاک
    -0.06
     Panc
    -0.06
    .GetData
    -0.06
     диза
    -0.06
    ouchers
    -0.06
     سبتمبر
    -0.06
    .reward
    -0.06
     Surrey
    -0.06
    POSITIVE LOGITS
     dove
    0.08
    ٫
    0.07
    ْل
    0.07
    َه
    0.07
    HAVE
    0.07
    IMUM
    0.06
     railing
    0.06
    cripcion
    0.06
     rst
    0.06
     clin
    0.06
    Act Density 0.001%

    No Known Activations