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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    _classes
    -0.08
     recognized
    -0.08
     recognised
    -0.07
     mov
    -0.07
    _UNSIGNED
    -0.07
     veins
    -0.07
     aug
    -0.07
     magn
    -0.07
     preprocessing
    -0.07
    irebase
    -0.07
    POSITIVE LOGITS
     אחי
    0.07
     Viktor
    0.07
    ⤺
    0.07
    が始
    0.06
     nobody
    0.06
     chặn
    0.06
     elites
    0.06
    łat
    0.06
     yüzde
    0.06
     Copies
    0.06
    Act Density 0.019%

    No Known Activations