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

    Neuronpedia

    INDEX
    Explanations

    counting and logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     πι
    0.45
    λιο
    0.44
    腳
    0.41
     joker
    0.40
     κυ
    0.39
     яви
    0.39
     النا
    0.39
     subparagraph
    0.38
    aisen
    0.38
     فيلم
    0.38
    POSITIVE LOGITS
    lesia
    0.43
     true
    0.43
    true
    0.42
    जूद
    0.41
    觎
    0.40
    屿
    0.39
     Ott
    0.39
    True
    0.39
     True
    0.38
     Czech
    0.38
    Act Density 10.223%

    No Known Activations