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

    Neuronpedia

    INDEX
    Explanations

    politics

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens related to politics, power struggles, and intrigue.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     PKK
    -0.07
     ماد
    -0.07
     ธ
    -0.07
     Kang
    -0.07
     anguish
    -0.07
    .csrf
    -0.06
     yak
    -0.06
    /train
    -0.06
    (customer
    -0.06
     대구
    -0.06
    POSITIVE LOGITS
     aspirations
    0.07
     самостоятельно
    0.07
    _URI
    0.06
    	static
    0.06
     Queens
    0.06
    После
    0.06
    oooooooo
    0.06
     perimeter
    0.06
    墙
    0.06
    	Runtime
    0.06
    Act Density 0.027%

    No Known Activations