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

    Neuronpedia

    INDEX
    Explanations

    keywords indicating programming code or structural elements

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

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite

    short code/math/technical tokens — e.g., programming identifiers, symbols, braces, backslashes and other non-natural-language token sequences.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ỗng
    -0.42
    Składniki
    -0.42
     surtido
    -0.41
     memiliki
    -0.41
     conformidad
    -0.40
     cremallera
    -0.40
     hierbas
    -0.39
     Aussch
    -0.39
     Gipfel
    -0.39
     ciasc
    -0.38
    POSITIVE LOGITS
     linkovi
    0.67
    +#+#
    0.65
    AccessorTable
    0.56
    httphttps
    0.55
     @"/
    0.53
    NameInMap
    0.53
     wireType
    0.52
    parsedMessage
    0.52
    FunctionFlags
    0.49
    contentLoaded
    0.49
    Act Density 0.000%

    No Known Activations