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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    قاء
    -0.07
     Summit
    -0.06
     il
    -0.06
    =path
    -0.06
    發
    -0.06
     عبر
    -0.06
    #ifdef
    -0.06
    (function
    -0.06
     collide
    -0.06
    꿸
    -0.06
    POSITIVE LOGITS
     dreaded
    0.08
    讨厌
    0.08
     אז
    0.08
     Antarctica
    0.08
    ())[
    0.07
     ży
    0.07
    爱国
    0.07
     palavra
    0.07
    _persona
    0.07
     enhances
    0.07
    Act Density 0.001%

    No Known Activations