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

    Neuronpedia

    INDEX
    Explanations

    descriptions of specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.91
    히
    0.84
    %-
    0.78
     นี้
    0.75
    비
    0.75
    힌
    0.74
    k
    0.72
    it
    0.71
     ambassador
    0.70
     एसडीएम
    0.70
    POSITIVE LOGITS
    ➢
    0.96
    ovaniyu
    0.92
     Стаўкі
    0.91
    olecules
    0.90
    各类
    0.89
     Гульнявыя
    0.86
     diseased
    0.85
     articulating
    0.84
    <unused1778>
    0.84
     gauging
    0.82
    Act Density 0.791%

    No Known Activations