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

    Neuronpedia

    INDEX
    Explanations

    dictatorships and politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Farmer
    -0.09
     Poker
    -0.08
     Lem
    -0.08
     Kash
    -0.08
     munch
    -0.08
     dairy
    -0.08
     Slack
    -0.08
     Remark
    -0.08
    ире
    -0.08
     farming
    -0.07
    POSITIVE LOGITS
     authoritarian
    0.16
     apartheid
    0.14
     dictatorship
    0.13
     oppressive
    0.12
     governments
    0.11
     regimes
    0.11
     dictators
    0.11
    政府
    0.10
     regime
    0.10
    民主
    0.10
    Act Density 0.034%

    No Known Activations