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

    Neuronpedia

    INDEX
    Explanations

    augment, ornamentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Caul
    1.27
    ্লাহ
    1.25
    iciency
    1.09
    𝗲
    1.08
    דת
    1.06
    ル
    1.05
    ্ট
    1.03
     Gorge
    1.03
    єю
    1.02
     Concise
    1.02
    POSITIVE LOGITS
    bbene
    1.41
    Appuntamento
    1.40
    ET
    1.36
    Avec
    1.34
     prilikom
    1.32
     involunt
    1.27
    ile
    1.25
    Czas
    1.25
    न्दावन
    1.25
    Ди
    1.24
    Act Density 0.102%

    No Known Activations