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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     naam
    -0.07
     fees
    -0.07
    春节期间
    -0.07
     ENERGY
    -0.07
     seinem
    -0.07
    Speed
    -0.07
     Marxism
    -0.07
    훓
    -0.07
    *C
    -0.06
    <Task
    -0.06
    POSITIVE LOGITS
    Like
    0.07
    �
    0.07
    oline
    0.06
    柔软
    0.06
    ordered
    0.06
     Take
    0.06
    _instances
    0.06
    bolt
    0.06
    洘
    0.06
     ought
    0.06
    Act Density 0.002%

    No Known Activations