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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     среди
    -0.07
    Å
    -0.07
    _override
    -0.07
    -ass
    -0.06
    硬
    -0.06
    (employee
    -0.06
     athletics
    -0.06
     Lawyer
    -0.06
     squared
    -0.06
     arcane
    -0.06
    POSITIVE LOGITS
     batching
    0.07
     ole
    0.06
    菲
    0.06
    loff
    0.06
    NECT
    0.06
    oute
    0.06
    (ast
    0.06
     Nhất
    0.06
    "",
    0.06
    λεί
    0.06
    Act Density 0.211%

    No Known Activations