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

    Neuronpedia

    INDEX
    Explanations

    happy expressive emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \...
    0.55
    \_
    0.55
    ……………………
    0.53
    -\\
    0.52
    \'{
    0.49
    …………………………………………
    0.48
    \-
    0.48
    ‐
    0.47
     coalitions
    0.45
    […]
    0.45
    POSITIVE LOGITS
     ❤️
    1.35
     ✨
    1.26
     ☑
    1.24
     ♥
    1.23
     😊
    1.22
     ❤
    1.17
     👍
    1.17
     🔥
    1.17
     ✅
    1.16
     😄
    1.16
    Act Density 0.211%

    No Known Activations