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

    Neuronpedia

    INDEX
    Explanations

    current state or situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑛
    1.13
    так
    1.12
    wenn
    1.07
     tils
    1.03
    ग
    0.98
     fermionic
    0.98
    น์
    0.96
    გ
    0.96
     অবহিত
    0.95
     подразуме
    0.95
    POSITIVE LOGITS
     Нужно
    1.02
     Mondial
    1.02
     Mga
    1.01
    ্টি
    1.00
    ECO
    1.00
     mistaken
    0.99
     ¿?
    0.98
    ей
    0.98
    equivariant
    0.98
    cups
    0.96
    Act Density 0.011%

    No Known Activations