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

    Neuronpedia

    INDEX
    Explanations

    words that are related to quality, innovation, improvement, or technological advance

    oai_token-act-pair · gemini-2.0-flash

    Reviews/Advancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.71
    IInterface
    -0.66
    ConverterFactory
    -0.64
     oprot
    -0.61
    CopyWith
    -0.60
    ChildScrollView
    -0.59
    HandlerContext
    -0.56
    postIndex
    -0.56
    WithIOException
    -0.56
    MergeFrom
    -0.55
    POSITIVE LOGITS
    <bos>
    0.84
     gimmick
    0.59
    //
    0.50
    brigens
    0.49
     novel
    0.48
    útil
    0.48
     quirks
    0.47
    eschön
    0.47
     localVar
    0.47
     gim
    0.46
    Act Density 1.666%

    No Known Activations