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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    杪
    -0.08
    (grammarAccess
    -0.07
     financier
    -0.07
    wä
    -0.07
     disproportionately
    -0.07
     vil
    -0.06
     ore
    -0.06
    政党
    -0.06
    より
    -0.06
     expended
    -0.06
    POSITIVE LOGITS
    _root
    0.07
    _wait
    0.07
     Blink
    0.07
    	root
    0.07
    inters
    0.07
     Invisible
    0.07
     Hollow
    0.06
    _Last
    0.06
     Idea
    0.06
    \Test
    0.06
    Act Density 0.059%

    No Known Activations