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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions with numbers and exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bbox>
    1.71
    的方法
    1.59
     Sudah
    1.55
    ുടെ
    1.53
    to
    1.52
    exion
    1.51
    liness
    1.51
    िता
    1.49
    ../
    1.48
    SERVICIO
    1.45
    POSITIVE LOGITS
    ва
    2.30
    ک
    2.28
    во
    1.70
    ваме
    1.70
     sofern
    1.70
    ான
    1.68
    ूतक
    1.61
    น
    1.61
    لی
    1.59
    胧
    1.57
    Act Density 0.057%

    No Known Activations