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

    Neuronpedia

    INDEX
    Explanations

    Administrative divisions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of administrative units and related terms (e.g. “district,” “municipality,” “Samtgemeinde,” “seat of”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    法院
    -0.07
    oday
    -0.06
    	page
    -0.06
    قلال
    -0.06
    Docs
    -0.06
    ďte
    -0.06
    .EndsWith
    -0.06
     savvy
    -0.06
    yal
    -0.06
    Enemies
    -0.06
    POSITIVE LOGITS
     デ
    0.07
     lỗ
    0.07
    (Json
    0.07
    respond
    0.06
     Assumes
    0.06
    _idle
    0.06
    çois
    0.06
    WithName
    0.06
     अपर
    0.06
    (Box
    0.06
    Act Density 0.007%

    No Known Activations