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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Hiện
    -0.08
     العشر
    -0.07
    فين
    -0.07
     جميل
    -0.07
     financier
    -0.07
     hiện
    -0.07
    	transform
    -0.06
    .flag
    -0.06
    	hash
    -0.06
    礼拜
    -0.06
    POSITIVE LOGITS
     WAN
    0.08
     losing
    0.07
     correl
    0.07
    ...')↵
    0.07
    坡
    0.07
     Ke
    0.07
    山区
    0.06
    辖区内
    0.06
     elic
    0.06
    えて
    0.06
    Act Density 0.005%

    No Known Activations