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

    Neuronpedia

    INDEX
    Explanations

    reading pages and what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.55
    short
    0.54
    zero
    0.52
    pro
    0.51
    by
    0.51
    stat
    0.51
    factory
    0.51
    without
    0.51
    international
    0.51
    no
    0.50
    POSITIVE LOGITS
    _*
    0.49
     truyện
    0.47
     ر
    0.47
     r
    0.46
    意见
    0.46
     _)
    0.46
    螺旋
    0.45
     returnPacket
    0.43
     Tukey
    0.43
     Sicht
    0.42
    Act Density 0.004%

    No Known Activations