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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _auc
    -0.07
    egrity
    -0.07
     Lear
    -0.06
    “There
    -0.06
    ussen
    -0.06
    òn
    -0.06
     OTHER
    -0.06
     Helsinki
    -0.06
     truy
    -0.06
     trunk
    -0.06
    POSITIVE LOGITS
     (:
    0.06
     fluctuations
    0.06
     __________________________________
    0.06
     Den
    0.06
     blev
    0.06
    AspectRatio
    0.06
     رابط
    0.06
    _coeffs
    0.06
    iscrimination
    0.06
    Activities
    0.06
    Act Density 0.051%

    No Known Activations