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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Elements
    -0.08
    ROID
    -0.08
    ish
    -0.07
     Manus
    -0.07
     doorway
    -0.07
     John
    -0.07
    腒
    -0.07
     sock
    -0.06
     initials
    -0.06
    (LayoutInflater
    -0.06
    POSITIVE LOGITS
    >(↵
    0.07
    竞争对手
    0.07
     العب
    0.07
    꿱
    0.07
     ==↵
    0.07
    رعا
    0.07
    *\
    0.06
     prueba
    0.06
     Huck
    0.06
    一邊
    0.06
    Act Density 0.006%

    No Known Activations