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

    Neuronpedia

    INDEX
    Explanations

    understanding how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     improves
    0.40
     Improves
    0.38
    推薦
    0.38
     notes
    0.38
     przej
    0.38
    겹
    0.38
     mala
    0.37
     Recommend
    0.37
    كرة
    0.37
     video
    0.36
    POSITIVE LOGITS
     যুক্তরাষ্ট্রের
    0.39
    ょう
    0.39
    JD
    0.39
     रीजनिंग
    0.39
    жны
    0.38
    subjects
    0.38
    صیلی
    0.37
     సంత
    0.37
    rekli
    0.37
    ত্যার
    0.37
    Act Density 0.000%

    No Known Activations