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

    Neuronpedia

    INDEX
    Explanations

    geographic locations

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of place names when listing administrative subdivisions (e.g., the names of communes or municipalities).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ATTER
    -0.07
    harma
    -0.07
    แ
    -0.06
     inve
    -0.06
    ासन
    -0.06
    forecast
    -0.06
     الخامسة
    -0.06
     businessman
    -0.06
    tod
    -0.06
     Smartphone
    -0.06
    POSITIVE LOGITS
    oenix
    0.07
     Aunt
    0.06
     şekilde
    0.06
    らない
    0.06
     کاهش
    0.06
    acích
    0.06
    .et
    0.06
    ังคม
    0.06
    _typeof
    0.06
    298
    0.05
    Act Density 0.028%

    No Known Activations