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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nós
    -0.08
    _lost
    -0.08
     pode
    -0.07
     Experts
    -0.07
     Конечно
    -0.07
     goes
    -0.07
     CATEGORY
    -0.07
     mogą
    -0.07
    ISA
    -0.06
     podemos
    -0.06
    POSITIVE LOGITS
    (ind
    0.07
    裒
    0.07
    פיל
    0.07
    structuring
    0.06
     Chrysler
    0.06
    ﴿
    0.06
     parch
    0.06
     אר
    0.06
    fa
    0.06
    〗
    0.06
    Act Density 0.581%

    No Known Activations