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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    双
    -0.06
     مادر
    -0.06
    (turn
    -0.06
    (dr
    -0.06
    (ob
    -0.06
     să
    -0.06
    /of
    -0.06
    里的
    -0.06
     gaz
    -0.06
     wisely
    -0.06
    POSITIVE LOGITS
    ={{
    0.06
    농
    0.06
    lore
    0.06
     halftime
    0.06
    bool
    0.06
    conti
    0.06
    ("[
    0.06
     swiper
    0.06
     önemlidir
    0.06
    ưng
    0.06
    Act Density 0.012%

    No Known Activations