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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Réponses
    -0.63
    saraba
    -0.61
    testcase
    -0.59
     Италијани
    -0.56
     الفلك
    -0.54
    Portale
    -0.54
    sidemargin
    -0.53
    évaluateur
    -0.52
    archiviato
    -0.52
    Jeografia
    -0.52
    POSITIVE LOGITS
     fabbrica
    0.66
     femininas
    0.63
     engraçadas
    0.57
    XMLSchema
    0.55
     vermelhas
    0.55
     brancas
    0.54
    method
    0.54
    ISupport
    0.53
     fabricantes
    0.53
    WithIOException
    0.52
    Act Density 0.735%

    No Known Activations