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

    Neuronpedia

    INDEX
    Explanations

    content related to freedom of expression and related rights

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

    legally-defined entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.52
    parsedMessage
    -0.47
    ChildScrollView
    -0.45
     cientí
    -0.44
    (/[
    -0.44
     principle
    -0.43
     الرياضيه
    -0.43
    Principle
    -0.43
    tonode
    -0.42
    FunctionFlags
    -0.41
    POSITIVE LOGITS
     المعيارى
    0.54
    gruntled
    0.47
    WAII
    0.47
     Moist
    0.43
     Handmaid
    0.42
    awtextra
    0.42
    Auguste
    0.40
    Everybody
    0.40
    aguay
    0.40
    liances
    0.39
    Act Density 0.009%

    No Known Activations