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

    Neuronpedia

    INDEX
    Explanations

    programming-related code structures and syntax elements

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

    character 'c' followed by float or code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lyst
    -0.46
     betweenstory
    -0.44
     fusca
    -0.44
    艋
    -0.44
     maus
    -0.41
     kerül
    -0.40
    握手
    -0.39
    发表于
    -0.39
    itness
    -0.39
     enf
    -0.38
    POSITIVE LOGITS
    rawDesc
    0.57
    +#+#
    0.54
    ariConfig
    0.50
    FunctionFlags
    0.50
     AssemblyCulture
    0.47
     disambiguazione
    0.44
    RefNanny
    0.43
    rebbero
    0.42
     للاسماء
    0.42
     calculated
    0.41
    Act Density 0.011%

    No Known Activations