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

    Neuronpedia

    INDEX
    Explanations

    military actions and territory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    бенок
    0.51
    质疑
    0.43
     الداله
    0.42
    妺
    0.42
     Photoc
    0.42
    ENCY
    0.41
    读
    0.41
    ຜະລິດຕ
    0.40
    arran
    0.40
    道歉
    0.40
    POSITIVE LOGITS
     combat
    0.58
     groupings
    0.54
    任務
    0.48
     subunits
    0.47
     Combat
    0.46
     grouping
    0.45
     전투
    0.45
     групи
    0.45
    剿
    0.44
     Actions
    0.44
    Act Density 0.003%

    No Known Activations