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

    Neuronpedia

    INDEX
    Explanations

    emphasizes importance, asks questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ítez
    0.50
    ज़र
    0.47
     SUNY
    0.45
     Extending
    0.45
     diario
    0.43
     scholar
    0.43
     Senior
    0.42
     रिश्ता
    0.41
     phục
    0.41
     Scholar
    0.41
    POSITIVE LOGITS
    هرات
    0.42
    悎
    0.40
    飲料
    0.39
    t
    0.38
    Emp
    0.38
     sphinct
    0.38
    rs
    0.38
    ることができます
    0.37
     кстати
    0.37
    を持
    0.37
    Act Density 0.013%

    No Known Activations