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

    Neuronpedia

    INDEX
    Explanations

    Create a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magazines
    0.78
     있어요
    0.77
     spokes
    0.75
     있는데
    0.74
     fullness
    0.74
     cedo
    0.74
     있으
    0.73
     газ
    0.72
     people
    0.72
    us
    0.72
    POSITIVE LOGITS
    ออกแบบ
    0.83
    Бы
    0.83
    führen
    0.79
    Kết
    0.77
    Де
    0.76
     optimized
    0.76
    Diện
    0.74
     capacité
    0.73
    <unused1907>
    0.73
     élég
    0.72
    Act Density 0.311%

    No Known Activations