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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and apostrophes in various contexts

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.73
     nahilalakip
    -0.72
    MessageTagHelper
    -0.68
    UrlResolution
    -0.64
     समीक्षाओं
    -0.63
    GeoNames
    -0.62
    CodeAttribute
    -0.61
     otomatig
    -0.61
     Chwiliwch
    -0.58
     فريبيس
    -0.57
    POSITIVE LOGITS
    object
    0.52
    string
    0.50
    undefined
    0.49
     object
    0.46
    function
    0.44
     string
    0.43
     function
    0.42
     overwhelming
    0.36
    <bos>
    0.35
     expectativa
    0.35
    Act Density 0.007%

    No Known Activations