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

    Neuronpedia

    INDEX
    Explanations

    quantities and orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۷
    0.97
    7
    0.96
    ７
    0.88
     seven
    0.83
     ۷
    0.81
    ٧
    0.80
    <0xB3>
    0.75
    ៧
    0.74
     sieben
    0.73
    ७
    0.73
    POSITIVE LOGITS
     cinq
    0.42
     छह
    0.37
    钰
    0.35
     ২৬
    0.35
     Ninth
    0.35
    仅
    0.35
    ື່ອ
    0.34
     cuyo
    0.34
     cinque
    0.34
     оценки
    0.34
    Act Density 0.242%

    No Known Activations