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

    Neuronpedia

    INDEX
    Explanations

    position binary sea Terror

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     used
    0.32
     that
    0.27
    radius
    0.25
     usable
    0.25
     parameter
    0.25
     সংখ্যক
    0.24
     groovy
    0.24
     able
    0.24
     useful
    0.24
     bytes
    0.24
    POSITIVE LOGITS
    ИА
    0.25
    Precio
    0.24
     المقبل
    0.24
    ﺠ
    0.24
    喜剧
    0.23
    웨
    0.23
    Ле
    0.23
    Стра
    0.23
     세계
    0.23
    났
    0.23
    Act Density 6.127%

    No Known Activations