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

    Neuronpedia

    INDEX
    Explanations

    avoids modifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Despatx
    0.44
     योर
    0.43
     scaleOf
    0.43
     diferença
    0.42
     ख़
    0.39
    ുകൾ
    0.39
    ⵅ
    0.38
    ቮ
    0.38
    ValueLayout
    0.37
    वेयर
    0.37
    POSITIVE LOGITS
     группа
    0.43
     grupo
    0.40
     концерт
    0.40
    дым
    0.40
    柏
    0.40
     Agg
    0.39
    นัก
    0.39
     freshmen
    0.39
    มอบ
    0.39
    0.38
    Act Density 0.004%

    No Known Activations