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

    Neuronpedia

    INDEX
    Explanations

    above, aforementioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Goy
    0.81
     prey
    0.81
    ỏa
    0.81
    潮
    0.80
     Geg
    0.79
     refle
    0.76
     mus
    0.75
     convuls
    0.75
     kho
    0.75
    交
    0.75
    POSITIVE LOGITS
     above
    1.79
    above
    1.76
    Above
    1.58
     foregoing
    1.55
    上記の
    1.53
    上述
    1.41
     ABOVE
    1.41
     Above
    1.40
     выше
    1.38
     acima
    1.35
    Act Density 0.647%

    No Known Activations