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

    Neuronpedia

    INDEX
    Explanations

    names of political figures or references to political leadership

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

    politicians and public figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #
    -0.51
     spic
    -0.47
    -0.47
     متعلقه
    -0.45
     okuyayım
    -0.45
     sugar
    -0.43
     spice
    -0.43
     nahilalakip
    -0.43
    __["
    -0.42
     Vern
    -0.41
    POSITIVE LOGITS
    phosa
    0.79
     Obrador
    0.57
     dezelve
    0.55
    IntoConstraints
    0.54
     ainfi
    0.53
     enfans
    0.50
     Económica
    0.50
    sonaro
    0.50
     määrä
    0.47
     mauva
    0.47
    Act Density 0.013%

    No Known Activations