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

    Neuronpedia

    INDEX
    Explanations

    States

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of national or service affiliations—i.e. country names, branch names, and related proper nouns (e.g. “United States,” “Navy,” “Italian Army,” “Royal Navy”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Elliott
    -0.06
     Moreno
    -0.06
    -git
    -0.06
    制造
    -0.06
    -css
    -0.06
    Monad
    -0.06
    _hit
    -0.06
    TRACE
    -0.06
     ❤
    -0.06
    -functional
    -0.06
    POSITIVE LOGITS
    rych
    0.07
    wei
    0.07
    ível
    0.07
    roj
    0.06
    وبة
    0.06
    Дата
    0.06
     *
    0.06
     boton
    0.06
     LOSS
    0.06
    ')
↵
↵
    0.06
    Act Density 0.025%

    No Known Activations