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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    庶
    -0.07
    新生
    -0.07
    .startActivity
    -0.07
     scored
    -0.07
    ipped
    -0.07
    _errors
    -0.07
     sports
    -0.07
    LL
    -0.07
    糇
    -0.07
     niños
    -0.07
    POSITIVE LOGITS
    認識
    0.08
     jak
    0.07
    вещ
    0.07
    Wy
    0.07
    owi
    0.07
     العلاقة
    0.07
    afort
    0.07
     结
    0.07
     Ди
    0.07
     Ap
    0.07
    Act Density 0.043%

    No Known Activations