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

    Neuronpedia

    INDEX
    Explanations

    export

    np_max-act · gemini-2.0-flash

    This neuron activates on trade-related terms, specifically the words “Import” and “Export.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MCC
    -0.07
    iar
    -0.06
    スカ
    -0.06
    Median
    -0.06
    ้องน
    -0.06
     딸
    -0.06
     Belly
    -0.06
    etas
    -0.06
     radar
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     queryInterface
    0.07
    (sum
    0.07
    (getClass
    0.07
     anticipate
    0.07
     exported
    0.07
     apologise
    0.07
     정보
    0.07
    programs
    0.06
    302
    0.06
    ../../
    0.06
    Act Density 0.004%

    No Known Activations