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

    Neuronpedia

    INDEX
    Explanations

    negative political commentary

    np_max-act · gemini-2.0-flash

    The neuron flags occurrences of “NRA,” “gun,” and related gun-control or pro-gun lobbying terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to named political entities—parties, organizations, government bodies, nationalities, and similar capitalized proper nouns in political discourse.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
     wen
    -0.06
    etections
    -0.06
     grinding
    -0.06
    jav
    -0.06
     submission
    -0.06
    #for
    -0.06
     muestra
    -0.06
     circulated
    -0.06
     gent
    -0.06
     gate
    -0.06
    POSITIVE LOGITS
    Del
    0.07
    (const
    0.07
    Οι
    0.06
     officer
    0.06
    -Am
    0.06
    ्रभ
    0.06
    ební
    0.06
    ＼＼
    0.06
    <KeyValuePair
    0.06
     Venezuela
    0.06
    Act Density 0.191%

    No Known Activations