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

    Neuronpedia

    INDEX
    Explanations

    function calls or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .),
    0.83
    .);
    0.76
     }}$.
    0.76
    .],
    0.75
    %),
    0.74
    %).
    0.74
    ))$.
    0.71
    .},
    0.69
    ."],
    0.68
    ."),
    0.68
    POSITIVE LOGITS
    (
    1.98
     (
    1.59
    (_
    1.53
    ($
    1.53
    ({
    1.48
    (&
    1.45
    ():
    1.41
    ([
    1.41
    (@
    1.40
    :(
    1.38
    Act Density 0.155%

    No Known Activations