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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsers
    -0.07
     Vander
    -0.07
     определ
    -0.06
    _agent
    -0.06
    商品
    -0.06
    copies
    -0.06
     genomes
    -0.06
     alan
    -0.06
     cigarettes
    -0.06
    ads
    -0.06
    POSITIVE LOGITS
    .firstChild
    0.07
    .cancel
    0.07
    ♥
    0.07
     Trio
    0.06
    是一个
    0.06
     Papa
    0.06
    ística
    0.06
    uenta
    0.06
     DAO
    0.06
    (seq
    0.06
    Act Density 0.075%

    No Known Activations