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

    Neuronpedia

    INDEX
    Explanations

    less

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     лишь
    -0.08
     Пост
    -0.08
     некоторое
    -0.08
     Endless
    -0.08
     очень
    -0.08
     Каждый
    -0.08
     પોસ્ટ
    -0.08
     infatti
    -0.08
     либо
    -0.07
     lembr
    -0.07
    POSITIVE LOGITS
    (input
    0.08
     pune
    0.08
     quantity
    0.07
     ones
    0.07
    bits
    0.07
    %,
    0.07
    課
    0.07
     siquiera
    0.07
    irik
    0.07
     chcete
    0.07
    Act Density 0.006%

    No Known Activations