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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming concepts and structures

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

    words before closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.39
     uns
    -0.36
     guaranteed
    -0.35
     easy
    -0.34
     vroe
    -0.33
    ↵
    -0.33
    setcounter
    -0.33
    -0.33
    ef
    -0.31
     longer
    -0.31
    POSITIVE LOGITS
     propOrder
    0.73
    enumii
    0.68
    parsedMessage
    0.66
     AssemblyCulture
    0.65
    IUrlHelper
    0.64
    enderror
    0.63
    utnik
    0.62
    SharedDtor
    0.61
    ſammen
    0.61
    windowFixed
    0.60
    Act Density 0.160%
    No Known Activations