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

    Neuronpedia

    INDEX
    Explanations

    class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aredo
    0.43
     on
    0.40
    šanas
    0.36
    BEGIN
    0.35
     SPI
    0.35
     व्हे
    0.35
     子
    0.35
     bus
    0.35
     SCALE
    0.35
     science
    0.35
    POSITIVE LOGITS
    морфи
    0.42
     nephritis
    0.42
    lcnaf
    0.41
    スナー
    0.41
    Adm
    0.41
     हेनरी
    0.41
     UnitTest
    0.40
    ட்டம்
    0.39
    oblasts
    0.39
    oeuvre
    0.39
    Act Density 0.000%

    No Known Activations