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

    Neuronpedia

    INDEX
    Explanations

    Italy and italian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    बाट
    1.13
    ड
    0.99
    ه
    0.95
    ید
    0.94
    ।
    0.94
    ם
    0.93
    لی
    0.91
    सँग
    0.90
    し
    0.89
    ⺊
    0.88
    POSITIVE LOGITS
     Itália
    1.44
     Итали
    1.39
     Italians
    1.34
     Italy
    1.24
    Italy
    1.24
     Italien
    1.23
     Италия
    1.19
    Italian
    1.14
     Италии
    1.12
     итальян
    1.05
    Act Density 0.013%

    No Known Activations