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

    Neuronpedia

    INDEX
    Explanations

    city

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of cities or urban place names (e.g., “city,” “New York City,” “Tokyo”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gelenek
    -0.07
     teknoloj
    -0.07
    694
    -0.07
     grp
    -0.07
    713
    -0.06
     яб
    -0.06
    theses
    -0.06
     cheerful
    -0.06
     classifications
    -0.06
    354
    -0.06
    POSITIVE LOGITS
    /V
    0.06
    ,/
    0.06
     watcher
    0.06
    情報
    0.06
     Nasıl
    0.06
     San
    0.06
     ENTITY
    0.06
    <small
    0.06
    /epl
    0.06
    _mag
    0.06
    Act Density 0.068%

    No Known Activations