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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deliberately
    -0.07
    My
    -0.06
     Chess
    -0.06
     сб
    -0.06
    ्र
    -0.06
     Pers
    -0.06
    umbai
    -0.06
    默
    -0.06
    ської
    -0.06
     Seeing
    -0.06
    POSITIVE LOGITS
     викон
    0.07
    大人
    0.06
     plc
    0.06
    }.${
    0.06
    可是
    0.06
    цип
    0.06
    _plot
    0.06
    /animate
    0.06
    roje
    0.06
     broadly
    0.06
    Act Density 0.000%

    No Known Activations