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

    Neuronpedia

    INDEX
    Explanations

    emojis with exclamation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ︎
    0.45
    🏻
    0.44
    🏼
    0.44
    ‿
    0.43
     seriously
    0.42
    😚
    0.42
    ㅋㅋㅋ
    0.42
     LOL
    0.41
    😝
    0.41
     lol
    0.41
    POSITIVE LOGITS
    isteren
    0.38
     वोल्ट
    0.38
    поте
    0.37
    puzzle
    0.37
    flask
    0.34
    Nested
    0.34
    Guru
    0.34
    idenza
    0.33
     ಪುಸ್ತಕ
    0.33
     কেননা
    0.33
    Act Density 0.016%

    No Known Activations