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

    Neuronpedia

    INDEX
    Explanations

    terms related to strictness and regulations

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

    strict rules or regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.49
    SuspendLayout
    -0.48
    utives
    -0.48
     '\\;'
    -0.48
    InjectAttribute
    -0.47
     <>",
    -0.47
    bootstrapcdn
    -0.47
    randomUUID
    -0.46
    mobileqq
    -0.46
     NSCoder
    -0.45
    POSITIVE LOGITS
     rules
    0.67
     policies
    0.66
     policy
    0.66
     stricter
    0.65
     restrictions
    0.65
     strict
    0.63
     laws
    0.59
     правила
    0.56
     Strict
    0.56
     rule
    0.56
    Act Density 0.127%

    No Known Activations