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

    Neuronpedia

    INDEX
    Explanations

    occurrences of input/output function calls in programming code

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

    programming output statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.84
    rungsseite
    -0.81
     незавершена
    -0.73
    __':
    -0.73
    __":
    -0.69
     disambiguazione
    -0.68
    __':
    -0.67
     onOptions
    -0.65
    TagMode
    -0.63
    Hochspringen
    -0.63
    POSITIVE LOGITS
    <![
    0.32
    idencial
    0.30
     löyty
    0.29
    NewReader
    0.28
     later
    0.28
    ั้น
    0.27
     fär
    0.27
     eerder
    0.26
     finnas
    0.26
     Befes
    0.26
    Act Density 0.009%

    No Known Activations