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

    Neuronpedia

    INDEX
    Explanations

    wine varietals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.58
    дах
    0.53
    ROS
    0.50
    َن
    0.50
    ANG
    0.48
    ROM
    0.47
    vapor
    0.46
    LLER
    0.45
    য়ান
    0.45
    iid
    0.45
    POSITIVE LOGITS
    ó
    0.59
     Pinot
    0.58
     testamentary
    0.55
     doctrina
    0.55
    se
    0.54
     Bantu
    0.54
     produce
    0.53
     artistic
    0.52
     к
    0.51
     ጥቅም
    0.51
    Act Density 0.002%

    No Known Activations