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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Divider
    -0.08
     bringen
    -0.07
     Erg
    -0.07
     appe
    -0.07
     paddingTop
    -0.06
     EW
    -0.06
     rotary
    -0.06
    อลล
    -0.06
    ebilecek
    -0.06
    lland
    -0.06
    POSITIVE LOGITS
     washed
    0.06
     smoothed
    0.06
    (panel
    0.06
     fucking
    0.06
    aza
    0.06
     jsem
    0.06
    اسة
    0.06
     breaking
    0.06
    (loop
    0.06
     actionTypes
    0.06
    Act Density 0.049%

    No Known Activations