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

    Neuronpedia

    INDEX
    Explanations

    emojis and hashtags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mathemat
    0.61
     principally
    0.59
     systemat
    0.59
     engender
    0.58
     일반적으로
    0.55
     பொதுவாக
    0.55
     preponder
    0.54
     explic
    0.53
     непосредственно
    0.52
     supposition
    0.52
    POSITIVE LOGITS
     😍
    1.03
    📸
    1.03
     ✨
    1.02
     🙌
    1.01
     🔥
    0.98
     💕
    0.98
     ❤️
    0.96
     💪
    0.95
     #
    0.95
     🥰
    0.95
    Act Density 0.090%

    No Known Activations