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

    Neuronpedia

    INDEX
    Explanations

    bypass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    793
    -0.07
     Burg
    -0.07
    upuncture
    -0.06
     submarines
    -0.06
    CONT
    -0.06
     ister
    -0.06
    contres
    -0.06
     meisjes
    -0.06
    Prepare
    -0.06
     confronting
    -0.06
    POSITIVE LOGITS
    .Getenv
    0.07
    %",
    0.06
    duit
    0.06
     Hint
    0.06
    ργ
    0.06
    .PictureBox
    0.06
    ()]
    0.06
    溪
    0.06
    vig
    0.06
    -sheet
    0.06
    Act Density 0.010%

    No Known Activations