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

    Neuronpedia

    INDEX
    Explanations

    living

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    惭
    -0.07
     ço
    -0.07
     Awards
    -0.07
    Vers
    -0.07
     giác
    -0.07
    ForegroundColor
    -0.07
    ây
    -0.06
    研
    -0.06
     clic
    -0.06
    绿水
    -0.06
    POSITIVE LOGITS
    )Math
    0.08
    ]),
    0.07
    -breaking
    0.07
    ┉
    0.07
     mismo
    0.07
    [w
    0.07
     unconstitutional
    0.07
    ),'
    0.07
    折扣
    0.07
    .');↵↵
    0.07
    Act Density 0.000%

    No Known Activations