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

    Neuronpedia

    INDEX
    Explanations

    references to noble characters or aristocracy

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

    noblemen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.46
    rungsseite
    -0.46
     怎样
    -0.46
     invokingState
    -0.41
     brunt
    -0.40
     становника
    -0.40
     Préférences
    -0.40
    itosti
    -0.38
    Shelter
    -0.38
    stamp
    -0.38
    POSITIVE LOGITS
    Noble
    0.71
     Noble
    0.69
    noble
    0.60
     noble
    0.57
     Nob
    0.49
    Nob
    0.48
    WebVitals
    0.48
     Nobles
    0.48
    NameInMap
    0.47
    TemporalType
    0.45
    Act Density 0.006%

    No Known Activations