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

    Neuronpedia

    INDEX
    Explanations

    quotations and dialogue in the text

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

    direct speech quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.54
    tagHelperRunner
    -0.53
    NUMX
    -0.48
    WebElementEntity
    -0.48
    :✨
    -0.48
     transférez
    -0.47
    farwyddwr
    -0.47
     مرئيه
    -0.46
    DoubleQuotes
    -0.45
     المرجع
    -0.45
    POSITIVE LOGITS
    还有
    0.48
     sonst
    0.46
    ick
    0.44
     ditto
    0.44
     alguien
    0.43
    Puedes
    0.43
     tampoco
    0.42
    That
    0.42
    someone
    0.42
    Could
    0.42
    Act Density 0.037%

    No Known Activations