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

    Neuronpedia

    INDEX
    Explanations

    films and documentaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	sleep
    -0.08
    ходят
    -0.07
     />
↵
    -0.07
    ruz
    -0.07
    stanbul
    -0.07
    ugi
    -0.07
             ↵
    -0.06
     haya
    -0.06
    ight
    -0.06
    alk
    -0.06
    POSITIVE LOGITS
    Orth
    0.08
    做工
    0.07
     exploits
    0.07
    ynos
    0.07
    :this
    0.07
    iom
    0.06
    (root
    0.06
    Concat
    0.06
    (board
    0.06
     CROSS
    0.06
    Act Density 0.032%

    No Known Activations