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

    Neuronpedia

    INDEX
    Explanations

    why changes were made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    1.14
    st
    1.12
    ל
    1.01
     interests
    0.99
    اء
    0.98
     independent
    0.94
    et
    0.91
    ם
    0.89
    িক
    0.87
    dependent
    0.87
    POSITIVE LOGITS
     layar
    1.25
     বিজ্ঞাপন
    1.25
    arı
    1.22
     فريبي
    1.20
     ফাইন
    1.18
     tanaman
    1.15
    графі
    1.15
    gx
    1.14
    晫
    1.13
     dessins
    1.11
    Act Density 0.000%

    No Known Activations