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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     which
    -0.08
    .IsTrue
    -0.08
     let
    -0.07
    Return
    -0.07
    請
    -0.07
     Let
    -0.07
     Intent
    -0.06
    總
    -0.06
     quite
    -0.06
     Get
    -0.06
    POSITIVE LOGITS
     AUD
    0.07
     ，
    0.07
    .Category
    0.06
    サイ
    0.06
     Tyson
    0.06
     paw
    0.06
     sınır
    0.06
    Archivo
    0.06
     rad
    0.06
    stad
    0.06
    Act Density 0.273%

    No Known Activations