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

    Neuronpedia

    INDEX
    Explanations

    references to object-oriented programming syntax and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `self` or `this` followed by a period

    np_acts-logits-general · gemini-2.0-flash

    self. or this. followed by identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.21
     itſelf
    -1.06
    OGND
    -1.04
    SourceChecksum
    -0.95
    GEBURTSDATUM
    -0.90
    featureID
    -0.87
     uſed
    -0.86
    '},
    -0.86
     whoſe
    -0.85
     EconPapers
    -0.85
    POSITIVE LOGITS
    .
    1.54
    ._
    0.84
    :
    0.75
    .,
    0.73
    ,
    0.71
     =
    0.69
    .:
    0.68
    ->
    0.64
    )
    0.64
    .-
    0.63
    Act Density 0.065%

    No Known Activations