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

    Neuronpedia

    INDEX
    Explanations

    square or prevent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ҫ
    1.19
    <unused542>
    1.17
     dàng
    1.16
    uyó
    1.16
    tuvo
    1.16
    ಗು
    1.14
     расстояние
    1.14
    vať
    1.13
     апреля
    1.11
    btnEjercicio
    1.10
    POSITIVE LOGITS
     parked
    1.03
    ak
    0.93
     pudd
    0.93
     tide
    0.91
     dolls
    0.91
     devel
    0.90
    ach
    0.90
     weeds
    0.88
    ig
    0.87
     Taman
    0.85
    Act Density 0.001%

    No Known Activations