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

    Neuronpedia

    INDEX
    Explanations

    for you, your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如果你
    0.47
     specifically
    0.45
     específicamente
    0.45
    വു
    0.41
    winner
    0.40
     puedes
    0.40
     relate
    0.39
    ர்க்
    0.39
     easy
    0.38
     naturels
    0.37
    POSITIVE LOGITS
    様々な
    0.44
    Reli
    0.43
     собі
    0.42
     자신
    0.42
    最高の
    0.41
     کررہ
    0.40
     apapun
    0.40
     дан
    0.39
     себе
    0.39
    etis
    0.39
    Act Density 0.040%

    No Known Activations