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

    Neuronpedia

    INDEX
    Explanations

    industry dominance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    комо
    0.45
    टिया
    0.44
    комен
    0.44
    Какие
    0.43
    Vaterpolo
    0.43
    Пред
    0.43
    เพื่อน
    0.43
    Tropical
    0.42
    Accessories
    0.42
    า
    0.42
    POSITIVE LOGITS
     änd
    0.48
    ↵
    0.45
     ==
    0.43
     Usage
    0.39
     =
    0.39
     destruction
    0.38
     يكون
    0.38
     JDK
    0.38
    ě
    0.38
     For
    0.38
    Act Density 0.012%

    No Known Activations