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

    Neuronpedia

    INDEX
    Explanations

    image dimensions height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coward
    0.39
    usehen
    0.39
    remember
    0.38
    wirk
    0.38
    sports
    0.37
     ሳ
    0.36
     sports
    0.35
     смотреть
    0.35
     dobl
    0.35
     hardware
    0.34
    POSITIVE LOGITS
    甙
    0.38
     високо
    0.37
    砺
    0.37
    FRING
    0.37
    HST
    0.36
    证
    0.36
     ແລະ
    0.35
    çin
    0.35
    чени
    0.35
    izado
    0.34
    Act Density 0.002%

    No Known Activations