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

    Neuronpedia

    INDEX
    Explanations

    unittest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지원
    -0.07
     Reyn
    -0.07
     europé
    -0.07
    ondon
    -0.07
    loy
    -0.06
     dj
    -0.06
    jad
    -0.06
    ुल
    -0.06
    给
    -0.06
     pozor
    -0.06
    POSITIVE LOGITS
    unittest
    0.07
    (unittest
    0.07
     unittest
    0.07
     unlink
    0.07
     مقاله
    0.06
    Ut
    0.06
    auth
    0.06
     UIColor
    0.06
     Sets
    0.06
     Nichols
    0.06
    Act Density 0.001%

    No Known Activations