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

    Neuronpedia

    INDEX
    Explanations

    friendly greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เภท
    0.61
     겁니다
    0.59
    場合があります
    0.58
     unchallenged
    0.58
     conclusive
    0.57
     temat
    0.56
     arbitrage
    0.56
    方向に
    0.56
    펼
    0.54
     আখ্যা
    0.54
    POSITIVE LOGITS
     hello
    1.09
     hi
    1.07
    hello
    1.05
     🥰
    1.05
     💕
    1.04
     ❤️
    1.03
     ❤
    0.99
     Hi
    0.99
     hii
    0.98
     cute
    0.98
    Act Density 0.444%

    No Known Activations