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

    Neuronpedia

    INDEX
    Explanations

    negative descriptions of people or groups

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

    title and role names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.39
     جه
    -0.37
     glitch
    -0.35
     glitches
    -0.34
     precedentes
    -0.34
    光明
    -0.34
     strukt
    -0.34
    ühungen
    -0.33
    elections
    -0.33
     struktur
    -0.33
    POSITIVE LOGITS
     myſelf
    0.72
     entrepreneur
    0.70
     Chriftian
    0.69
     Citizen
    0.66
    Citizen
    0.66
     Entrepreneur
    0.66
     citizen
    0.65
    Leader
    0.63
    Entrepreneur
    0.63
     Warrior
    0.61
    Act Density 0.190%

    No Known Activations