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

    Neuronpedia

    INDEX
    Explanations

    United States

    np_max-act · gemini-2.0-flash

    This neuron detects references to countries or national/regional identities (e.g., demonyms and nation names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    AVE
    -0.07
    David
    -0.07
    .jsdelivr
    -0.07
     Hoy
    -0.07
     Lis
    -0.07
     amateurs
    -0.06
     jel
    -0.06
     Filipino
    -0.06
    	org
    -0.06
    ,current
    -0.06
    POSITIVE LOGITS
     vary
    0.07
    xious
    0.07
    看到
    0.07
    看见
    0.07
     леж
    0.07
     στην
    0.06
    eft
    0.06
     searchable
    0.06
    ('/:
    0.06
    .Include
    0.06
    Act Density 0.116%

    No Known Activations