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

    Neuronpedia

    INDEX
    Explanations

    list item numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     demás
    0.35
    ﺗ
    0.35
    पणा
    0.35
    మని
    0.34
     flotte
    0.34
     paragraphe
    0.34
    কালে
    0.34
     baud
    0.33
     altri
    0.33
     পদ্ধতির
    0.33
    POSITIVE LOGITS
    ️⃣
    0.71
    ⃣
    0.57
    :
    0.50
    ของการ
    0.50
    ′
    0.48
    ″
    0.47
     của
    0.41
    ের
    0.40
    :"
    0.39
    nd
    0.38
    Act Density 0.092%

    No Known Activations