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

    Neuronpedia

    INDEX
    Explanations

    political views, assault and battery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.47
    処理
    0.41
     a
    0.40
    लेट्स
    0.40
     Refresh
    0.39
     ढक
    0.38
     সঙ্ক
    0.38
     witch
    0.38
     घरी
    0.38
     magic
    0.38
    POSITIVE LOGITS
     எதுவும்
    0.49
     vuttam
    0.48
     solcher
    0.48
    거나
    0.47
     или
    0.43
     أعلى
    0.42
    ׁ
    0.42
     alebo
    0.42
     корпус
    0.42
     Или
    0.42
    Act Density 0.000%

    No Known Activations