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

    Neuronpedia

    INDEX
    Explanations

    hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erz
    0.46
     lên
    0.44
    elijkheid
    0.44
     эр
    0.43
    eraj
    0.42
    lubridate
    0.42
    itions
    0.41
    षित
    0.40
    toto
    0.40
    ()%
    0.39
    POSITIVE LOGITS
     conceptual
    0.46
     hand
    0.44
    手
    0.40
     abundant
    0.39
    動
    0.39
     modular
    0.39
    帳
    0.39
     ample
    0.38
     behaviour
    0.38
    ेद
    0.38
    Act Density 0.000%

    No Known Activations