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

    Neuronpedia

    INDEX
    Explanations

    the structural elements of a programming context, specifically related to questions and categories in a coding environment

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

    "category" or "categories" token

    np_acts-logits-general · gemini-2.0-flash

    category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.76
    VersionUID
    -0.76
     utafitiHapana
    -0.73
    Rüyada
    -0.72
    rungsseite
    -0.71
    complexContent
    -0.66
    IUrlHelper
    -0.63
    aarrggbb
    -0.63
    awtextra
    -0.63
    HtmlAttribute
    -0.62
    POSITIVE LOGITS
     category
    3.17
     Category
    2.92
    category
    2.81
     categories
    2.78
    Category
    2.74
     Categories
    2.53
     CATEGORY
    2.50
    CATEGORY
    2.40
     getCategory
    2.39
    categories
    2.35
    Act Density 0.285%

    No Known Activations