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

    Neuronpedia

    INDEX
    Explanations

    Soviet

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “Soviet” (especially “Soviet Union”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gl
    -0.07
     luder
    -0.07
     दल
    -0.07
     kn
    -0.06
     Archbishop
    -0.06
     신청
    -0.06
     ка
    -0.06
     elephant
    -0.06
    ,address
    -0.06
     Golden
    -0.06
    POSITIVE LOGITS
     Soviet
    0.14
    actual
    0.08
    essian
    0.08
     Soviets
    0.08
     revolving
    0.07
     совет
    0.07
    oriented
    0.07
     Vote
    0.07
     Sov
    0.07
    vv
    0.07
    Act Density 0.004%

    No Known Activations