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

    Neuronpedia

    INDEX
    Explanations

    this is a car

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العلم
    0.46
     жить
    0.46
    佺
    0.45
     द्विवेदी
    0.45
     ዕ
    0.44
     एग्जामिनेशन
    0.44
    ിക
    0.43
    䇞
    0.43
     ഹോളി
    0.42
     supplementation
    0.42
    POSITIVE LOGITS
    orbits
    0.44
     organizações
    0.42
     barracks
    0.41
    er
    0.41
    en
    0.41
    qi
    0.41
     policies
    0.41
    reachable
    0.40
    rmi
    0.40
     projetos
    0.40
    Act Density 0.002%

    No Known Activations