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

    Neuronpedia

    INDEX
    Explanations

    expectation and likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ngữ
    1.05
     impetus
    1.03
    ूद
    1.02
    蝰
    1.02
     enchantment
    1.01
     giống
    1.00
     storytelling
    0.99
     Tiến
    0.99
     tên
    0.98
     ominous
    0.98
    POSITIVE LOGITS
    ا
    1.38
    ان
    1.26
    Nicht
    1.25
    اء
    1.20
     وعلى
    1.13
    ї
    1.12
    ่
    1.11
    त
    1.09
    ä
    1.09
    ك
    1.04
    Act Density 0.290%

    No Known Activations