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

    Neuronpedia

    INDEX
    Explanations

    state changes and manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sifatida
    0.36
     Дон
    0.33
     imprescindible
    0.33
    ிலே
    0.33
    ilihan
    0.33
     ஆகும்
    0.32
     situada
    0.32
     fáciles
    0.32
     نفسي
    0.32
    جیب
    0.32
    POSITIVE LOGITS
     успешно
    0.46
     successfully
    0.45
     unexpectedly
    0.42
     prematurely
    0.41
     somewhere
    0.41
     concurrently
    0.41
     alongside
    0.38
     along
    0.38
     globally
    0.38
     correctly
    0.38
    Act Density 0.120%

    No Known Activations