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

    Neuronpedia

    INDEX
    Explanations

    vocal, nuanced, tech, pound

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    щення
    0.52
     পোষ্ট
    0.49
    ولوژی
    0.49
    іль
    0.48
    ailure
    0.48
    ्युनिकेशन
    0.48
    વારે
    0.47
    имость
    0.47
    ię
    0.47
    뜨
    0.45
    POSITIVE LOGITS
    Ig
    0.48
    MO
    0.48
     k
    0.47
    reas
    0.47
     Peer
    0.45
     الجزء
    0.45
    Proto
    0.45
     조
    0.45
     dt
    0.45
     Go
    0.44
    Act Density 0.001%

    No Known Activations