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

    Neuronpedia

    INDEX
    Explanations

    opening curly braces in code snippets

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

    code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olverine
    -0.60
     pleaſure
    -0.59
     ویکی‌آمباردا
    -0.54
    endpush
    -0.53
     SPDX
    -0.53
    ziasztok
    -0.52
    exitRule
    -0.52
    Ӕ
    -0.52
     betweenstory
    -0.51
    majánló
    -0.50
    POSITIVE LOGITS
    SequentialGroup
    0.51
    KommentareTeilen
    0.47
     {
    0.43
    colgroup
    0.39
     useCallback
    0.38
    :^{
    0.35
     oops
    0.33
    ParallelGroup
    0.33
    useEffect
    0.32
    BufferException
    0.32
    Act Density 0.021%

    No Known Activations