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

    Neuronpedia

    INDEX
    Explanations

    hall, robots, Mercury, distributed datasets, trace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cud
    0.47
     Perez
    0.45
     юбилей
    0.45
     Pere
    0.45
     RP
    0.44
     даже
    0.44
     много
    0.43
     очеред
    0.43
     програ
    0.43
    5
    0.42
    POSITIVE LOGITS
     並
    0.49
    ক
    0.45
    」，
    0.44
    。
    0.44
     monetize
    0.43
    ൻ
    0.43
     개의
    0.43
    ။
    0.43
     तत्
    0.42
     ይችላል
    0.42
    Act Density 0.002%

    No Known Activations