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

    Neuronpedia

    INDEX
    Explanations

    descending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (@
    -0.07
     गत
    -0.07
    below
    -0.07
     H�
    -0.07
     plenty
    -0.06
     homework
    -0.06
     Αγ
    -0.06
    >Welcome
    -0.06
     rep
    -0.06
     Βασ
    -0.06
    POSITIVE LOGITS
    目的
    0.07
     uncertainty
    0.07
    (false
    0.07
     AppleWebKit
    0.06
     crossword
    0.06
     useMemo
    0.06
     Collision
    0.06
    (piece
    0.06
    ヾ
    0.06
     dex
    0.06
    Act Density 0.006%

    No Known Activations