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

    Neuronpedia

    INDEX
    Explanations

    External

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    新京
    -0.07
    指控
    -0.07
     wlan
    -0.07
    ccd
    -0.07
     riff
    -0.07
     Miy
    -0.07
    昀
    -0.07
     uf
    -0.06
     contestant
    -0.06
    ᒌ
    -0.06
    POSITIVE LOGITS
    allel
    0.08
    tol
    0.08
    (rest
    0.07
     Serv
    0.07
     Buttons
    0.07
     *@
    0.07
    oped
    0.07
    atically
    0.07
    itories
    0.07
    	ST
    0.07
    Act Density 0.002%

    No Known Activations