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

    Neuronpedia

    INDEX
    Explanations

    Romanian language and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ।--
    0.63
     вікі
    0.63
    ಞ
    0.63
    тування
    0.62
     وغیرہ
    0.61
     بیاکت
    0.61
    Ⲩ
    0.60
     باسکٹ
    0.59
     کمار
    0.59
    ائیو
    0.58
    POSITIVE LOGITS
     Romanian
    2.11
     Romania
    1.98
     Bucharest
    1.89
    Romania
    1.67
     Bucure
    1.64
     România
    1.59
     Cluj
    1.53
     Moldova
    1.30
    ă
    1.27
     în
    1.25
    Act Density 0.010%

    No Known Activations