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

    Neuronpedia

    INDEX
    Explanations

    adding items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Differences
    0.39
    şa
    0.39
    Differ
    0.37
     Differences
    0.37
    ષા
    0.37
     বণ্ট
    0.37
    াশ
    0.36
    σκεται
    0.36
     sagt
    0.36
    Example
    0.36
    POSITIVE LOGITS
     hinzu
    1.34
     added
    1.04
     доба
    1.04
     добавля
    1.02
     add
    1.00
     thêm
    0.97
     добавить
    0.96
     добав
    0.95
     hinzufügen
    0.94
     adicion
    0.93
    Act Density 0.049%

    No Known Activations