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

    Neuronpedia

    INDEX
    Explanations

    armed

    np_max-act · gemini-2.0-flash

    narratives or statements about environmental issues or crises.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on words referring to military contexts—terms like military, armed, forces, troops, defense, invasion, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Italians
    -0.08
    utherland
    -0.07
     sogar
    -0.07
    过去
    -0.07
    /************************
    -0.07
     Malk
    -0.07
     เจ
    -0.06
    celand
    -0.06
    iner
    -0.06
    füh
    -0.06
    POSITIVE LOGITS
     زي
    0.07
     armed
    0.06
     serge
    0.06
     Armed
    0.06
     Soldier
    0.06
     Arms
    0.06
     express
    0.06
     skilled
    0.06
     assertion
    0.06
     GetValue
    0.06
    Act Density 0.011%

    No Known Activations