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

    Neuronpedia

    INDEX
    Explanations

    words that are used in the context of writing a review

    oai_token-act-pair · gemini-2.0-flash

    Movies and genes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     препратки
    -0.69
    <bos>
    -0.66
     Wikimedijinoj
    -0.65
    EndGlobalSection
    -0.62
    Geplaatst
    -0.59
    parsedMessage
    -0.59
    zeciw
    -0.59
    новништво
    -0.58
    adaptiveStyles
    -0.56
    NameInMap
    -0.54
    POSITIVE LOGITS
     corret
    0.48
    wój
    0.48
    RenderAtEndOf
    0.46
    üht
    0.45
    visející
    0.43
    VersionUID
    0.43
    asantry
    0.41
    レクト
    0.41
    quire
    0.41
    #}
    0.41
    Act Density 7.123%

    No Known Activations