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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lost
    -0.08
    长大了
    -0.07
     أخي
    -0.07
    一緒
    -0.07
    경영
    -0.07
     Released
    -0.07
     Freddie
    -0.07
    OfMonth
    -0.07
     contraceptive
    -0.07
    _Space
    -0.07
    POSITIVE LOGITS
    𝚜
    0.07
    _D
    0.07
    imageName
    0.07
    𝑵
    0.07
    ramer
    0.07
    午饭
    0.06
    榴
    0.06
    Ρ
    0.06
    压
    0.06
     Km
    0.06
    Act Density 0.001%

    No Known Activations