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

    Neuronpedia

    INDEX
    Explanations

    queries and statements expressing uncertainty or conditions related to decision-making

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

    preceding "a" or "of" (with context)

    np_acts-logits-general · gemini-2.0-flash

    whether, ignored, or sexist comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.38
     useParams
    -0.31
     createSlice
    -0.31
    Diweddarwch
    -0.30
    PageIndex
    -0.30
     Grüsse
    -0.30
    OrNil
    -0.30
    ">//
    -0.30
     particularly
    -0.29
     getRule
    -0.28
    POSITIVE LOGITS
     فريبيس
    0.61
    LabelTagHelper
    0.54
    addCriterion
    0.54
    IndentedString
    0.53
    UrlResolution
    0.53
    hyrchwyd
    0.52
    InputTagHelper
    0.50
    󠁴
    0.49
     Вікіпе
    0.47
    telemetry
    0.46
    Act Density 0.529%

    No Known Activations