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

    Neuronpedia

    INDEX
    Explanations

    military units and ranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eateries
    0.45
    FUEL
    0.42
    ৈতিক
    0.41
     miliardi
    0.41
     socialista
    0.40
     健康
    0.39
     childish
    0.39
     totalitarian
    0.39
     যানবাহ
    0.38
     metabolites
    0.38
    POSITIVE LOGITS
     Infantry
    0.76
     Regiment
    0.70
     Brigade
    0.58
     brigade
    0.57
     Mounted
    0.57
     infantry
    0.56
     Cavalry
    0.55
     রেজিম
    0.55
     Airborne
    0.54
     regiments
    0.54
    Act Density 0.030%

    No Known Activations