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

    Neuronpedia

    INDEX
    Explanations

    complete your requests thoughtfully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     것을
    0.43
     قال
    0.42
    Votre
    0.42
     가진
    0.41
     Tinggi
    0.41
    十五
    0.41
     Tất
    0.40
     glLight
    0.40
    తో
    0.40
     Thiết
    0.40
    POSITIVE LOGITS
     merupakan
    0.39
     rownames
    0.39
    ಿಕ
    0.39
    兵庫
    0.39
     HashMap
    0.38
    هم
    0.38
    ={()
    0.38
    ੂੰ
    0.37
    Hundreds
    0.37
    डम
    0.37
    Act Density 0.090%

    No Known Activations