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

    Neuronpedia

    INDEX
    Explanations

    underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dependencies
    -0.08
     możliwość
    -0.08
    _memory
    -0.08
     HEADER
    -0.07
    辨别
    -0.07
    atem
    -0.07
     patrons
    -0.07
     의견
    -0.07
     selectedIndex
    -0.07
    -good
    -0.07
    POSITIVE LOGITS
    羔
    0.08
    变革
    0.08
    xx
    0.07
     Naval
    0.07
    PubMed
    0.07
    Serial
    0.07
    Spatial
    0.07
    gr
    0.07
    uclear
    0.07
    .af
    0.07
    Act Density 0.048%

    No Known Activations