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

    Neuronpedia

    INDEX
    Explanations

    numbers and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لكن
    0.46
     მაგრამ
    0.44
     mutta
    0.43
    但是在
    0.42
     lakini
    0.42
    ஆனால்
    0.42
     nhưng
    0.41
     салу
    0.40
     pero
    0.39
     ولكن
    0.39
    POSITIVE LOGITS
     wichtigen
    0.46
    WOOD
    0.44
    यु
    0.41
     ว่า
    0.40
     unquestion
    0.40
    zocht
    0.40
     würde
    0.39
     tych
    0.39
    委
    0.39
     vhod
    0.39
    Act Density 0.034%

    No Known Activations