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

    Neuronpedia

    INDEX
    Explanations

    non-English and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuestra
    0.45
    util
    0.42
     Family
    0.42
    <0xE3>
    0.41
    飞
    0.41
    וני
    0.40
     desapare
    0.39
    RAM
    0.39
    Suzanne
    0.39
    uan
    0.39
    POSITIVE LOGITS
    ।...
    0.49
    zovaniyu
    0.46
     말미암
    0.46
     ऐप्स
    0.46
     स्टार्टिंग
    0.46
     ponctué
    0.46
     ଯ
    0.46
    ዣ
    0.45
     ponctuées
    0.45
    ).^
    0.45
    Act Density 0.001%

    No Known Activations