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

    Neuronpedia

    INDEX
    Explanations

    rounding numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atta
    -0.08
    манд
    -0.08
    textarea
    -0.08
    GUILayout
    -0.08
     Consum
    -0.08
    保证
    -0.08
    <header
    -0.08
    .Content
    -0.08
     reutil
    -0.08
     Tirol
    -0.08
    POSITIVE LOGITS
     rounding
    0.16
     rounded
    0.10
     ROUND
    0.10
     round
    0.10
    _round
    0.10
    .round
    0.09
    rounded
    0.09
     midpoint
    0.09
     rounds
    0.09
    (round
    0.09
    Act Density 0.025%

    No Known Activations