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

    Neuronpedia

    INDEX
    Explanations

    executed directly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    그리고
    0.45
    alt
    0.43
    programming
    0.41
    编程
    0.41
     programming
    0.40
    chen
    0.40
    ()-
    0.39
    contenido
    0.39
    oce
    0.39
    Programming
    0.39
    POSITIVE LOGITS
     Jayne
    0.45
     Viewed
    0.40
     Pink
    0.40
     Malgré
    0.39
     viewed
    0.39
    നോ
    0.39
     tratt
    0.38
     Пі
    0.38
    想起
    0.38
     особое
    0.38
    Act Density 0.009%

    No Known Activations