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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     MORE
    -0.07
     stdin
    -0.07
     min
    -0.07
    YNAM
    -0.07
     Sounds
    -0.07
    死刑
    -0.07
     Month
    -0.06
     gunmen
    -0.06
     revenues
    -0.06
    新年
    -0.06
    POSITIVE LOGITS
    ퟮ
    0.08
    缢
    0.07
     TCP
    0.07
    هز
    0.07
    翱
    0.07
    ᵖ
    0.07
     bei
    0.07
     cropped
    0.07
    ≅
    0.07
    пу
    0.07
    Act Density 0.012%

    No Known Activations