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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Token
    -0.07
    伯
    -0.06
    產品
    -0.06
     clinging
    -0.06
    奥
    -0.06
    ляється
    -0.06
    illin
    -0.06
    atorial
    -0.06
    mf
    -0.06
     ль
    -0.06
    POSITIVE LOGITS
    ÖL
    0.07
     이용
    0.06
     ihtiyac
    0.06
    	W
    0.06
     consequence
    0.06
     smirk
    0.06
    して
    0.06
     иму
    0.06
    (asset
    0.06
     cigaret
    0.06
    Act Density 0.014%

    No Known Activations