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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marilyn
    -0.06
    	s
    -0.06
     hvě
    -0.06
     lstm
    -0.06
    _pw
    -0.06
     pp
    -0.06
     граду
    -0.06
    acho
    -0.06
    ‌شود
    -0.05
     chess
    -0.05
    POSITIVE LOGITS
     reel
    0.08
    bohydr
    0.07
    λη
    0.06
     mam
    0.06
    скую
    0.06
    .$.
    0.06
    -mobile
    0.06
    .On
    0.06
    .Ptr
    0.06
    interval
    0.06
    Act Density 0.012%

    No Known Activations