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

    Neuronpedia

    INDEX
    Explanations

    suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    רגש
    -0.07
     scand
    -0.07
    <IM
    -0.07
    情
    -0.07
    Pink
    -0.07
     --------
    -0.07
    סל
    -0.07
    (IService
    -0.06
     Desire
    -0.06
    ("<
    -0.06
    POSITIVE LOGITS
     suffix
    0.08
    _suffix
    0.07
     Wed
    0.07
    Inject
    0.07
     salary
    0.07
     watt
    0.07
    uffix
    0.07
    	Y
    0.07
    圉
    0.07
     Ans
    0.07
    Act Density 0.006%

    No Known Activations