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

    Neuronpedia

    INDEX
    Explanations

    references to historical political figures and their roles

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

    before titles (king, emperor, tsar)

    np_acts-logits-general · gemini-2.0-flash

    royal succession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WaitGroup
    -0.63
    XmlAccessType
    -0.61
     الرياضيه
    -0.56
    OrBuilder
    -0.50
     Pfarrer
    -0.48
    انيف
    -0.47
    insee
    -0.46
    wpi
    -0.45
    lée
    -0.45
     technician
    -0.45
    POSITIVE LOGITS
     king
    1.51
     King
    1.44
     kings
    1.43
     royal
    1.41
     monarch
    1.37
     throne
    1.35
     monarchs
    1.32
     royalty
    1.27
     monarchy
    1.25
     royals
    1.24
    Act Density 0.609%

    No Known Activations