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

    Neuronpedia

    INDEX
    Explanations

    occurrences of backticks in the text

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

    words in backticks or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.45
     OFDb
    -0.43
     maxX
    -0.42
     startIndex
    -0.41
     dataList
    -0.40
     magasiner
    -0.40
    errHandler
    -0.39
     تعدى
    -0.39
     Ganze
    -0.38
     foly
    -0.38
    POSITIVE LOGITS
     `
    1.23
    =`
    1.09
    :`
    1.05
    (`
    1.05
     (`
    1.02
     "`
    0.95
    {`
    0.91
     '`
    0.88
    ={`
    0.87
     ``
    0.86
    Act Density 0.010%

    No Known Activations