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

    Neuronpedia

    INDEX
    Explanations

    occurrences of function declarations in programming code

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

    `void` method declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.73
     autorytatywna
    -0.65
     كومونز
    -0.59
     indígen
    -0.56
     transfieras
    -0.55
     queſta
    -0.55
    TagMode
    -0.54
     ModelExpression
    -0.54
     Paglinawan
    -0.53
     mijne
    -0.52
    POSITIVE LOGITS
     also
    0.57
     To
    0.48
    LET
    0.47
    let
    0.46
     let
    0.45
     pula
    0.45
    PCell
    0.44
     Th
    0.44
     Let
    0.44
     TO
    0.43
    Act Density 0.003%

    No Known Activations