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

    Neuronpedia

    INDEX
    Explanations

    medical diagnosis and treatments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.38
    OL
    0.32
    的
    0.31
    UC
    0.31
     katika
    0.30
     silice
    0.30
     phóng
    0.29
     swirl
    0.29
     tavern
    0.29
    ௦
    0.29
    POSITIVE LOGITS
     for
    0.36
    n
    0.34
    ти
    0.33
    tom
    0.33
    ਾ
    0.33
     advancements
    0.31
     achievements
    0.30
    c
    0.30
    st
    0.29
    x
    0.29
    Act Density 0.095%

    No Known Activations