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

    Neuronpedia

    INDEX
    Explanations

    Countries

    np_max-act · gemini-2.0-flash

    The neuron fires on country names and national demonyms (e.g. “American,” “United States,” “British,” “Cuba”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Authorization
    -0.07
    scan
    -0.07
    eday
    -0.07
     pois
    -0.06
    Pizza
    -0.06
     weddings
    -0.06
     Commission
    -0.06
    _glob
    -0.06
    .Head
    -0.06
    Size
    -0.06
    POSITIVE LOGITS
    rowsers
    0.06
     ві
    0.06
    	content
    0.06
     Siemens
    0.06
    .EditText
    0.06
     stren
    0.06
    atabase
    0.06
    ?>
↵
    0.06
     avan
    0.06
    arness
    0.06
    Act Density 0.028%

    No Known Activations