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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     duas
    0.52
     Uma
    0.48
     uma
    0.46
    遜
    0.45
     dois
    0.45
     forne
    0.44
     burrito
    0.44
     stora
    0.42
     ainsi
    0.41
    رى
    0.41
    POSITIVE LOGITS
    integration
    0.41
    swadian
    0.39
    challenge
    0.38
    ະພັນ
    0.38
    비
    0.38
    िंग्स
    0.37
    ಳಿತ
    0.37
    би
    0.37
    debut
    0.37
    ७
    0.37
    Act Density 0.001%

    No Known Activations