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

    Neuronpedia

    INDEX
    Explanations

    words related to reading articles, showing interest or desire, or applying

    oai_token-act-pair · gemini-2.0-flash

    reading and interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.58
    Географиясе
    -0.56
    GEBURTSDATUM
    -0.52
    WithIOException
    -0.51
    idados
    -0.51
    elebr
    -0.49
    发表于
    -0.49
    -0.48
    ResponseWriter
    -0.48
    endregion
    -0.47
    POSITIVE LOGITS
    VersionUID
    0.63
    RefNanny
    0.58
    enumi
    0.58
     Theſe
    0.57
     Diſ
    0.56
     écou
    0.56
    :^(
    0.56
    ISupport
    0.54
     cháy
    0.54
    робнее
    0.53
    Act Density 3.044%

    No Known Activations