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

    Neuronpedia

    INDEX
    Explanations

    a specific formatting or layout structure within the text

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

    Appears at the beginning of a line

    np_acts-logits-general · gemini-2.0-flash

    self state Jesus himself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RoutedEventArgs
    -0.60
    KommentareTeilen
    -0.52
     g
    -0.52
    g
    -0.52
     spin
    -0.51
     and
    -0.50
     L
    -0.50
     Tro
    -0.50
    getColumnIndex
    -0.49
     snippetHide
    -0.49
    POSITIVE LOGITS
    1.30
     myſelf
    1.27
    1.16
     ſtate
    1.07
    1.04
     Jefus
    1.01
     himſelf
    1.01
     itſelf
    1.00
     beſt
    0.99
     pleaſure
    0.99
    Act Density 0.953%

    No Known Activations