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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    	local
    -0.07
     het
    -0.06
    하시는
    -0.06
    (defun
    -0.06
     dünyan
    -0.06
    	Button
    -0.06
    ')")↵
    -0.06
    Ǟ
    -0.06
    殇
    -0.06
     bachelor
    -0.06
    POSITIVE LOGITS
    野外
    0.07
    车型
    0.07
    Level
    0.07
     IDisposable
    0.07
    АЗ
    0.06
    女性朋友
    0.06
    研究
    0.06
    zx
    0.06
    фер
    0.06
     Grant
    0.06
    Act Density 0.036%

    No Known Activations