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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific formatting or symbols in text

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

    technical programming comments

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

    This neuron detects numeric tokens — numbers, years, measurements, zip/postal codes and other digit sequences (including decimals).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.66
     AssemblyCompany
    -0.62
    OGND
    -0.56
    :✨
    -0.55
    Composable
    -0.52
    ########.
    -0.52
    脚注の使い方
    -0.52
    -0.50
    SharedCtor
    -0.50
    +#+#
    -0.48
    POSITIVE LOGITS
    Externé
    0.32
    __":
    0.32
     отли
    0.31
    *)
    0.29
    __*/
    0.28
    UnsafeEnabled
    0.28
    somewhat
    0.26
    MigrationBuilder
    0.26
    errHandler
    0.26
    */;
    0.26
    Act Density 1.258%

    No Known Activations