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

    Neuronpedia

    INDEX
    Explanations

    coding syntax elements and constructs commonly used in programming languages

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

    creating new mutable data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doors
    -0.41
     nahilalakip
    -0.38
    strcpy
    -0.37
    pushFollow
    -0.37
     strlen
    -0.35
     wind
    -0.35
    あり
    -0.34
     let
    -0.34
     gates
    -0.33
     MATCH
    -0.33
    POSITIVE LOGITS
    BeginInit
    0.56
     new
    0.48
    basicConfig
    0.47
     }{@
    0.46
     empty
    0.44
    ffindor
    0.44
    ValueGeneration
    0.43
    تقاوى
    0.43
     Sơ
    0.43
    AllAfrica
    0.43
    Act Density 0.012%

    No Known Activations