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

    Neuronpedia

    INDEX
    Explanations

    social media engagement symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engender
    0.64
     பொதுவாக
    0.54
     상당히
    0.53
     principally
    0.52
    非常に
    0.52
     আরম্ভ
    0.50
     biographical
    0.50
    십시오
    0.50
     idiosyncratic
    0.49
     preponder
    0.48
    POSITIVE LOGITS
     #
    1.70
     @
    1.43
     ✨
    1.26
     🙌
    1.26
     👀
    1.21
     @_
    1.20
     🔥
    1.18
     💪
    1.14
     ❤️
    1.08
     👇
    1.08
    Act Density 0.049%

    No Known Activations