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

    Neuronpedia

    INDEX
    Explanations

    code implementing date formatting

    oai_token-act-pair · gemini-2.0-flash

    Dates and formatting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     himſelf
    -0.75
     myſelf
    -0.69
     pleaſure
    -0.68
     themſelves
    -0.66
     greateſt
    -0.66
    UnknownFieldSet
    -0.65
    sữa
    -0.65
     reaſon
    -0.65
    pexpr
    -0.65
     faſt
    -0.65
    POSITIVE LOGITS
    الإنجليزية
    0.59
    SequentialGroup
    0.43
     $__
    0.42
    yyyy
    0.42
    NgModule
    0.41
    dddd
    0.40
     []:
    0.40
     Corintios
    0.40
    '");
    0.39
    MMdd
    0.37
    Act Density 13.688%

    No Known Activations