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

    Neuronpedia

    INDEX
    Explanations

    sliced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achelor
    -0.07
     comparative
    -0.07
    的话
    -0.06
    coach
    -0.06
     Played
    -0.06
     alertController
    -0.06
    VP
    -0.06
    钐
    -0.06
    	record
    -0.06
     expect
    -0.06
    POSITIVE LOGITS
    .connected
    0.08
    봣
    0.07
     zwłaszcza
    0.07
    从容
    0.07
    一首
    0.07
    מסורת
    0.06
    úde
    0.06
     Harmon
    0.06
    迥
    0.06
    .';↵
    0.06
    Act Density 0.010%

    No Known Activations