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

    Neuronpedia

    INDEX
    Explanations

    references to functions, constructors, and object initialization

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

    Deals with default or initialized values

    np_acts-logits-general · gemini-2.0-flash

    default values and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.81
    rrggbb
    -0.72
    ftagPool
    -0.62
    بوابة
    -0.61
     oprot
    -0.58
     CommandType
    -0.57
     ErrIntOverflow
    -0.56
     Convex
    -0.56
    strando
    -0.56
     onOptions
    -0.55
    POSITIVE LOGITS
    memset
    1.39
     초기
    1.25
     initial
    1.12
     initialize
    1.08
     reset
    1.06
     defaults
    1.06
     default
    1.04
    initial
    1.04
     zeros
    1.03
     initialization
    1.02
    Act Density 0.298%

    No Known Activations