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

    Neuronpedia

    INDEX
    Explanations

    safety, emergency, warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lacht
    0.53
    as
    0.52
    wert
    0.49
    lama
    0.49
    zeta
    0.49
    have
    0.49
    pecific
    0.48
    bias
    0.48
    zn
    0.47
    ent
    0.47
    POSITIVE LOGITS
    开
    0.59
     juices
    0.50
    你们
    0.49
     tổng
    0.48
     hiệu
    0.48
    빌
    0.48
     вас
    0.47
    ນ
    0.47
    เต็ม
    0.46
     người
    0.46
    Act Density 0.001%

    No Known Activations