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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores and related formatting elements

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

    external validator parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.55
     Paglinawan
    -0.54
    enumii
    -0.52
     betweenstory
    -0.51
    Personendaten
    -0.47
    tagext
    -0.45
     NSCoder
    -0.44
     arşivlendi
    -0.44
    +#+#
    -0.43
     financeira
    -0.42
    POSITIVE LOGITS
    uxxxx
    0.60
     pinulongan
    0.47
    rrggbb
    0.43
     Nadu
    0.41
    PAI
    0.41
     Glanz
    0.41
    ̣i
    0.41
     pleaſure
    0.41
    cupa
    0.40
     yyb
    0.40
    Act Density 0.000%

    No Known Activations