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

    Neuronpedia

    INDEX
    Explanations

    places and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoặc
    0.62
     eller
    0.60
     nebo
    0.59
     or
    0.59
     oder
    0.57
     atau
    0.56
     లేదా
    0.56
     vagy
    0.53
     \"
    0.52
     Velcro
    0.52
    POSITIVE LOGITS
     военных
    0.59
    military
    0.57
     выстав
    0.56
     যুদ্ধের
    0.56
    naval
    0.55
    порт
    0.55
     соору
    0.55
     возле
    0.53
    戰爭
    0.53
     uprising
    0.52
    Act Density 0.001%

    No Known Activations