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

    Neuronpedia

    INDEX
    Explanations

    formatting and punctuation elements within text, particularly quotation marks and italics

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

    academic/book titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.74
    AndEndTag
    -0.68
    sizeCache
    -0.68
     pinulongan
    -0.66
     Wikiseite
    -0.66
     disambiguazione
    -0.66
    rungsseite
    -0.65
    HtmlAttribute
    -0.64
    expandindo
    -0.64
    FunctionFlags
    -0.63
    POSITIVE LOGITS
    <i>
    0.56
    The
    0.49
    『
    0.47
    <h1>
    0.44
     The
    0.43
     『
    0.42
    <b>
    0.42
    <h3>
    0.42
    《
    0.42
     ואת
    0.42
    Act Density 0.000%

    No Known Activations