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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Trường
    -0.08
     Adult
    -0.07
     transformed
    -0.07
     Sloan
    -0.07
    ikon
    -0.07
    (Job
    -0.07
    ucz
    -0.07
     prefers
    -0.07
    武装
    -0.07
    ⇜
    -0.06
    POSITIVE LOGITS
    毗邻
    0.07
    碧
    0.07
     glanced
    0.07
    ▄
    0.06
    跟她
    0.06
    _connected
    0.06
    一带
    0.06
     FACT
    0.06
    เบ
    0.06
    阏
    0.06
    Act Density 0.000%

    No Known Activations