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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    illie
    0.38
     toward
    0.37
    ントリー
    0.37
     Silica
    0.37
     personally
    0.36
    បន្ថ
    0.36
     picnics
    0.36
    ظم
    0.35
     unt
    0.35
    ಗು
    0.35
    POSITIVE LOGITS
    rxjs
    0.45
    rss
    0.41
    kusen
    0.41
    entet
    0.40
     ফেব্রুয়ার
    0.40
    archiv
    0.39
    佽
    0.39
    🎉
    0.39
    From
    0.39
    的基础上
    0.38
    Act Density 0.002%

    No Known Activations