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

    Neuronpedia

    INDEX
    Explanations

    Poland and Polish things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     venezolano
    0.61
    цију
    0.57
     اولمپس
    0.54
    நபியே
    0.54
     essentially
    0.53
    ҳа
    0.52
     Oahu
    0.52
     Ayurvedic
    0.51
     آمریک
    0.51
     Essentially
    0.51
    POSITIVE LOGITS
     Polish
    2.33
     Poland
    2.14
    Polish
    2.13
     поль
    2.02
    Poland
    2.02
     Поль
    1.98
     Polska
    1.82
     Pologne
    1.81
     Warsaw
    1.77
     Kraków
    1.77
    Act Density 0.054%

    No Known Activations