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

    Neuronpedia

    INDEX
    Explanations

    references to programming interfaces and repository patterns

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

    code and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.66
    RotationOrder
    -0.63
    DataAnnotations
    -0.62
    NBT
    -0.62
    ſelves
    -0.61
     itſelf
    -0.59
    bcryptjs
    -0.58
     Houſe
    -0.57
    AddHtmlAttribute
    -0.56
     Jefus
    -0.56
    POSITIVE LOGITS
    HtmlAttribute
    1.31
    bson
    1.13
     bson
    1.05
     الحره
    0.92
    AfterClass
    0.70
     Lesnar
    0.70
     calldata
    0.68
    Bson
    0.59
     actionPerformed
    0.54
    دانشنامهٔ
    0.45
    Act Density 0.001%

    No Known Activations