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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Pune
    -0.08
     får
    -0.07
    .getText
    -0.07
     puedes
    -0.07
    襲
    -0.07
    getPosition
    -0.06
     Unused
    -0.06
    opaque
    -0.06
    何处
    -0.06
     sque
    -0.06
    POSITIVE LOGITS
    交换
    0.07
    efault
    0.07
     drugs
    0.07
    員工
    0.07
    updates
    0.06
     editors
    0.06
    叫
    0.06
     classifiers
    0.06
     slowed
    0.06
     corn
    0.06
    Act Density 0.017%

    No Known Activations