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

    Neuronpedia

    INDEX
    Explanations

    modulo operations and remainders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kezi
    0.47
    ellers
    0.45
    gwood
    0.45
    EnglishMarks
    0.45
    ეგისტრ
    0.44
    সান
    0.44
    %@",
    0.43
    rocery
    0.43
    णासाठी
    0.42
    playerCards
    0.42
    POSITIVE LOGITS
    0.58
     v
    0.50
     modulo
    0.50
    7
    0.47
     ?
    0.47
     mod
    0.46
    6
    0.46
    1
    0.46
     \
    0.45
     Mod
    0.45
    Act Density 0.002%

    No Known Activations