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

    Neuronpedia

    INDEX
    Explanations

    size of the universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.45
    だけ
    0.44
    美容
    0.42
    呂
    0.42
     überprü
    0.42
     दग
    0.42
    люми
    0.42
    Pixel
    0.40
     انسٹ
    0.40
    ermat
    0.39
    POSITIVE LOGITS
     always
    0.53
     abundant
    0.48
     seas
    0.48
     leagues
    0.46
     (
    0.46
     league
    0.45
     infinite
    0.45
     travelers
    0.44
     endless
    0.44
     passengers
    0.44
    Act Density 0.005%

    No Known Activations