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

    Neuronpedia

    INDEX
    Explanations

    matrix concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.52
    al
    0.47
     نهاية
    0.46
     Цвет
    0.44
    ill
    0.44
    igraf
    0.43
     Кам
    0.43
    ed
    0.43
    ult
    0.42
    higher
    0.41
    POSITIVE LOGITS
     rewarding
    0.46
    ادری
    0.46
    坸
    0.46
    🈺
    0.45
     एरिया
    0.44
     ০
    0.44
     ০৯
    0.43
    cimiento
    0.42
    푠
    0.42
    율
    0.42
    Act Density 0.001%

    No Known Activations