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

    Neuronpedia

    INDEX
    Explanations

    sentences summarizing experimental results, especially those containing the words "results" or "findings".

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.44
     Hoboken
    -0.44
    nasio
    -0.44
    VIER
    -0.43
     oficial
    -0.43
     kız
    -0.43
    płat
    -0.42
     Ayrıca
    -0.42
     endblock
    -0.42
     conclusive
    -0.42
    POSITIVE LOGITS
    سطس
    0.64
    chymal
    0.60
    MigrationBuilder
    0.60
    WireFormatLite
    0.59
    IndentedString
    0.57
    openqa
    0.56
     Réponses
    0.56
     NUKAT
    0.56
     QtWidgets
    0.55
     estimés
    0.55
    Act Density 1.130%

    No Known Activations