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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Losing
    -0.07
    .Configure
    -0.06
    男士
    -0.06
    贈
    -0.06
    鹎
    -0.06
    셥
    -0.06
     usleep
    -0.06
    웅
    -0.06
    するのが
    -0.06
     Discovery
    -0.06
    POSITIVE LOGITS
    yz
    0.07
    灵活性
    0.07
    ﺑ
    0.07
     ха
    0.07
    -six
    0.07
     ниже
    0.07
    𝒊
    0.07
    床垫
    0.06
    -switch
    0.06
    marginLeft
    0.06
    Act Density 0.049%

    No Known Activations