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

    Neuronpedia

    INDEX
    Explanations

    venues and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pine
    0.40
    茆
    0.39
     pend
    0.38
    ہوری
    0.38
    礽
    0.38
    पक्ष
    0.37
     Cruises
    0.37
    itimes
    0.37
    تبقى
    0.36
    uais
    0.36
    POSITIVE LOGITS
     Но
    0.41
    ƒ
    0.40
     стратегия
    0.40
     вме
    0.38
     применения
    0.38
     capacities
    0.38
    óch
    0.38
    īng
    0.38
     уме
    0.38
    Мы
    0.37
    Act Density 0.034%

    No Known Activations