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

    Neuronpedia

    INDEX
    Explanations

    emojis like 🚀, 👇, 🤪, 🥳

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2222>
    0.93
    <unused2140>
    0.92
    <unused2197>
    0.88
    [multimodal]
    0.88
    --“
    0.87
    --"
    0.86
    "--
    0.80
    ”।
    0.80
    <unused2117>
    0.78
    <unused2173>
    0.78
    POSITIVE LOGITS
     ❤️
    2.04
     ✨
    2.03
     ✅
    1.94
     👇
    1.85
    ✨
    1.80
     🔥
    1.80
     💪
    1.76
     🤔
    1.74
     🌱
    1.72
    ❤️
    1.67
    Act Density 0.995%

    No Known Activations