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

    Neuronpedia

    INDEX
    Explanations

    detailed explanation or breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旁
    0.51
    每天
    0.49
    និយាយ
    0.47
    提到
    0.47
     notebook
    0.45
     thí
    0.45
     সভাপতিত্ব
    0.44
     쪽
    0.43
     ভারপ্রাপ্ত
    0.42
    好了
    0.41
    POSITIVE LOGITS
    🗽
    0.50
    UTR
    0.49
    нії
    0.47
    OTO
    0.46
    醾
    0.45
    ONY
    0.45
    दुर्
    0.45
     ܐ
    0.45
    AC
    0.44
    บู
    0.44
    Act Density 0.002%

    No Known Activations