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

    Neuronpedia

    INDEX
    Explanations

    conflict

    np_max-act · gemini-2.0-flash

    The neuron detects words that name or describe major crises—especially armed conflicts and their humanitarian impacts (e.g. “war,” “conflict,” “famine,” “battle,” “torn,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ZONE
    -0.07
    	Il
    -0.07
    	Point
    -0.07
    يل
    -0.07
     Rainbow
    -0.07
     Morgan
    -0.07
     dancers
    -0.06
    Args
    -0.06
    "(
    -0.06
     Dresses
    -0.06
    POSITIVE LOGITS
     namoro
    0.07
     BaseEntity
    0.06
    ắp
    0.06
     参数
    0.06
     deceit
    0.06
     supern
    0.06
    idual
    0.06
    ้ด
    0.06
     topl
    0.06
    娜
    0.06
    Act Density 0.033%

    No Known Activations