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

    Neuronpedia

    INDEX
    Explanations

    function calls or method invocations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused915>
    0.72
     (\<
    0.71
    <unused603>
    0.71
    sinya
    0.70
    <unused609>
    0.70
    […]
    0.69
    <unused628>
    0.68
     (…)
    0.67
     कंप्र
    0.67
     식이
    0.67
    POSITIVE LOGITS
    ↵
    0.51
    0.49
    //{
    0.48
    ++
    0.46
    <unused60>
    0.45
     life
    0.43
    let
    0.42
    ?
    0.41
    ::
    0.40
     straight
    0.39
    Act Density 0.371%

    No Known Activations