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

    Neuronpedia

    INDEX
    Explanations

    sides or opposite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     산
    0.56
    ீர்கள்
    0.56
     미
    0.55
    ίζουν
    0.55
    しょう
    0.54
     մե
    0.54
     ملا
    0.54
    <0x8C>
    0.53
    すすめ
    0.52
     ähnlich
    0.52
    POSITIVE LOGITS
     side
    4.62
    Side
    4.06
     Side
    4.03
    side
    3.79
     SIDE
    3.53
     sides
    3.34
    側
    3.32
    SIDE
    3.14
     lado
    3.08
    側の
    2.99
    Act Density 0.168%

    No Known Activations