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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saraba
    -0.88
    WriteBarrier
    -0.77
     للمعارف
    -0.68
    发表于
    -0.67
    ativement
    -0.66
    RegistryLite
    -0.63
    InjectAttribute
    -0.62
     kasarigan
    -0.60
     gepubliceerd
    -0.59
    TagMode
    -0.58
    POSITIVE LOGITS
     disambiguazione
    0.56
     */;
    0.55
    .
    0.53
     désolés
    0.53
    .
    0.46
    .",
    0.46
    ;
    0.45
    лат
    0.45
     fine
    0.45
    classnames
    0.44
    Act Density 0.001%

    No Known Activations