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

    Neuronpedia

    INDEX
    Explanations

    list markers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ✨
    1.36
     pacif
    1.33
     💪
    1.33
     🙌
    1.32
     🙏
    1.29
     ⭐
    1.28
     🔥
    1.26
     mantra
    1.26
     ¬
    1.26
     😘
    1.25
    POSITIVE LOGITS
    (
    1.84
    [
    1.80
    {
    1.74
    "
    1.67
    //
    1.58
    $
    1.57
    #
    1.42
    *
    1.40
    \
    1.35
    --
    1.33
    Act Density 1.231%

    No Known Activations