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

    Neuronpedia

    INDEX
    Explanations

    explaining conceptual or technical steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াইড
    0.32
     ডাক্তার
    0.32
    ：
    0.30
     Do
    0.29
     didn
    0.29
    ด้าน
    0.29
     announced
    0.29
    スマホ
    0.28
     ech
    0.28
     télécharg
    0.28
    POSITIVE LOGITS
     mẫu
    0.33
    Incidentally
    0.32
     غادي
    0.31
     complej
    0.31
     probabilidades
    0.30
    稷
    0.30
     немно
    0.30
    尒
    0.30
     иных
    0.29
     manifestly
    0.29
    Act Density 0.147%

    No Known Activations