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

    Neuronpedia

    INDEX
    Explanations

    heat instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biệt
    0.48
     rappro
    0.42
    ーー
    0.41
     केलेल्या
    0.41
    ফের
    0.39
     ทั้ง
    0.38
    ត្ថ
    0.38
     Bein
    0.38
    Both
    0.38
     effectué
    0.38
    POSITIVE LOGITS
    🥣
    0.40
    ন্ত্রী
    0.40
     магнит
    0.38
     開始
    0.38
    鸚
    0.38
    Schools
    0.38
    इंडिया
    0.38
     ಕಲ
    0.38
     ಜನ
    0.37
    漳
    0.37
    Act Density 0.019%

    No Known Activations