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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kam
    -0.07
    Gi
    -0.07
    付出
    -0.07
     minimise
    -0.07
     Sage
    -0.07
     GPA
    -0.07
    -Shirt
    -0.06
    :test
    -0.06
    شهور
    -0.06
     Lama
    -0.06
    POSITIVE LOGITS
    인터
    0.07
     permalink
    0.07
     near
    0.07
     międ
    0.06
     comercial
    0.06
     LOAD
    0.06
    零
    0.06
    VarInsn
    0.06
    믹
    0.06
    §Ã
    0.06
    Act Density 0.017%

    No Known Activations