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

    Neuronpedia

    INDEX
    Explanations

    之外

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Steam
    -0.08
     steam
    -0.08
     Steam
    -0.07
    Lifestyle
    -0.07
    ieft
    -0.07
     Enkel
    -0.07
    arkan
    -0.07
    '}↵↵
    -0.07
     truths
    -0.07
     stationed
    -0.07
    POSITIVE LOGITS
     Except
    0.09
    pendicular
    0.08
     remot
    0.08
     Submit
    0.08
    Except
    0.08
     yaklaşık
    0.08
     बै
    0.08
    (border
    0.08
     excluding
    0.07
     अधिकांश
    0.07
    Act Density 0.001%

    No Known Activations