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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming constructs and documentation in code

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

    code documentation keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unknownFields
    -0.73
     وتسجيلات
    -0.65
     utafitiHapana
    -0.58
     المعيارى
    -0.57
    AndEndTag
    -0.56
     NSCoder
    -0.55
    colnshire
    -0.52
    InputBorder
    -0.52
    principalTable
    -0.52
     InputDecoration
    -0.52
    POSITIVE LOGITS
    theoremstyle
    0.48
     Everybody
    0.47
    Everybody
    0.42
    Nobody
    0.41
    aarrggbb
    0.40
     Thier
    0.39
    bool
    0.39
     Everyone
    0.39
     Since
    0.38
     Though
    0.38
    Act Density 0.036%

    No Known Activations