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

    Neuronpedia

    INDEX
    Explanations

    voters

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on occurrences of the word “voter(s),” i.e. references to people casting ballots.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enia
    -0.07
    اشته
    -0.07
     сна
    -0.07
    ania
    -0.06
     mnohem
    -0.06
    ponse
    -0.06
    _done
    -0.06
    -widgets
    -0.06
     Summary
    -0.06
    куля
    -0.06
    POSITIVE LOGITS
     voters
    0.12
     voter
    0.10
     Voter
    0.08
     Voters
    0.08
     electorate
    0.08
    व
    0.07
    -dr
    0.07
    Polit
    0.06
    PER
    0.06
    调查
    0.06
    Act Density 0.002%

    No Known Activations