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

    Neuronpedia

    INDEX
    Explanations

    important statistical concepts and metrics

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

    specific actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.38
    igrafi
    -0.32
    derung
    -0.30
     net
    -0.29
    ⓧ
    -0.29
     Näch
    -0.29
     brukar
    -0.28
    quiagem
    -0.27
     Bedien
    -0.26
     yyr
    -0.26
    POSITIVE LOGITS
    Билгалдахарш
    0.64
    FunctionFlags
    0.60
     الاطلاع
    0.60
    HideFlags
    0.59
    Климат
    0.58
    elebr
    0.58
     linkovi
    0.58
     فريبيس
    0.57
    consulté
    0.57
    +#+
    0.55
    Act Density 0.749%

    No Known Activations