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

    Neuronpedia

    INDEX
    Explanations

    mentions of someone speaking, telling, or otherwise communicating information.

    oai_token-act-pair · gemini-2.0-flash

    telling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -0.71
     pleaſure
    -0.70
     Theſe
    -0.69
     Jefus
    -0.68
    SourceChecksum
    -0.65
     Diſ
    -0.65
     Reſ
    -0.60
     '\\;'
    -0.60
     ModelExpression
    -0.59
     myſelf
    -0.59
    POSITIVE LOGITS
     Se
    0.56
    ração
    0.52
     us
    0.52
    !*\
    0.51
    जन
    0.50
    AutoScaleMode
    0.49
    ها
    0.48
    neté
    0.48
    EDITOR
    0.48
    QMetaType
    0.47
    Act Density 0.344%

    No Known Activations