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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     విద్య
    -0.09
    ాత్ర
    -0.08
     Assess
    -0.07
     महिल
    -0.07
    idents
    -0.07
     Signs
    -0.07
     verlie
    -0.07
     wyn
    -0.07
     మహిళ
    -0.07
     Zhang
    -0.07
    POSITIVE LOGITS
     ENV
    0.08
    .EN
    0.08
    ầ
    0.08
     avanzado
    0.07
    .Identifier
    0.07
     compromis
    0.07
    類
    0.07
     liber
    0.07
    -enable
    0.07
     declara
    0.07
    Act Density 0.005%

    No Known Activations