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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Eng
    -0.07
     순간
    -0.06
    Map
    -0.06
    NEL
    -0.06
     Wagner
    -0.06
    Buffer
    -0.06
    cart
    -0.06
     Nap
    -0.06
     Zuckerberg
    -0.06
     Parkinson
    -0.06
    POSITIVE LOGITS
     bồi
    0.06
    较
    0.06
    metis
    0.06
     اقتص
    0.06
     чоловік
    0.06
     غیر
    0.06
    işleri
    0.06
    closing
    0.06
    Do
    0.06
    (argument
    0.06
    Act Density 0.024%

    No Known Activations