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

    Neuronpedia

    INDEX
    Explanations

    instances of names and titles related to authority figures

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

    security team

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.61
    SequentialGroup
    -0.58
     المعيارى
    -0.55
    styleType
    -0.54
    EndContext
    -0.54
    出版年
    -0.51
     pouvoit
    -0.50
     Normdatei
    -0.50
     للمعارف
    -0.49
    WindowConstants
    -0.49
    POSITIVE LOGITS
    oredCriteria
    0.34
    腹
    0.33
    kane
    0.33
     fist
    0.33
     outfit
    0.32
    findpost
    0.31
    cade
    0.31
     cadre
    0.31
    tack
    0.31
    Geografia
    0.30
    Act Density 0.053%

    No Known Activations