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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash

    This neuron activates on words naming centers or focal areas—e.g. “hubs,” “markets,” “hotspots”—marking key locations or domains.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cus
    -0.08
    ise
    -0.07
    ちゃん
    -0.07
    izes
    -0.07
     Буд
    -0.07
     Pose
    -0.07
     USC
    -0.07
    たり
    -0.06
     Brendan
    -0.06
     scan
    -0.06
    POSITIVE LOGITS
    .STRING
    0.07
     hands
    0.06
     Dayton
    0.06
    입니다
    0.06
    .coordinate
    0.06
     contender
    0.06
     国家
    0.06
     suburb
    0.06
    '),
    0.06
     فرودگاه
    0.05
    Act Density 0.063%

    No Known Activations