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

    Neuronpedia

    INDEX
    Explanations

    references to permission or access control issues within a technical context

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

    code and math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.73
    ValueStyle
    -0.67
     NSCoder
    -0.66
     propOrder
    -0.62
    StoryboardSegue
    -0.62
     disambiguazione
    -0.60
    DoubleQuotes
    -0.60
    Autoritní
    -0.60
    HtmlAttribute
    -0.59
    expandindo
    -0.59
    POSITIVE LOGITS
    mtr
    0.40
    Doc
    0.39
    Global
    0.38
    \{\\
    0.38
    <!--
    0.36
     Dolan
    0.36
     обла
    0.35
    NewLine
    0.35
    MR
    0.35
    langle
    0.35
    Act Density 0.059%

    No Known Activations