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

    Neuronpedia

    INDEX
    Explanations

    terms and structures related to code changes or diffs in programming

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

    git diff index information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whole
    -0.28
    <eos>
    -0.26
    -------------</
    -0.25
     dé
    -0.24
     ganzen
    -0.24
     hasta
    -0.23
     until
    -0.23
    ีย
    -0.23
    <0xE2>
    -0.23
     ven
    -0.22
    POSITIVE LOGITS
     EconPapers
    1.02
    SequentialGroup
    0.85
    UrlResolution
    0.83
     NSCoder
    0.82
     للمعارف
    0.82
     Roskov
    0.80
    makeConstraints
    0.80
     surla
    0.79
    0.77
    ंदीखरीदारी
    0.77
    Act Density 0.009%

    No Known Activations