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

    Neuronpedia

    INDEX
    Explanations

    city locations and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    2.16
     sich
    1.63
     been
    1.61
    ați
    1.60
    €¦
    1.58
    i
    1.56
     distinto
    1.45
    ्युनिटी
    1.41
     अज
    1.41
    .`);
    1.39
    POSITIVE LOGITS
    ia
    2.00
     dwellers
    1.74
    특별시
    1.69
     slick
    1.64
    esque
    1.63
     приз
    1.60
    ла
    1.56
    City
    1.56
     skyscrapers
    1.54
     случа
    1.54
    Act Density 0.225%

    No Known Activations