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

    Neuronpedia

    INDEX
    Explanations

    kn, knot, knit, knight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मस्कार
    0.46
     चारा
    0.42
    萋
    0.42
    צר
    0.41
     cereal
    0.41
    सीजी
    0.41
     اچ
    0.41
    蚩
    0.38
    仓
    0.38
     শিশ
    0.38
    POSITIVE LOGITS
    Kn
    3.69
     Kn
    3.59
     kn
    3.55
    kn
    3.45
     KN
    3.28
    KN
    3.11
     Knights
    2.97
     Knight
    2.94
     Knox
    2.86
     knight
    2.84
    Act Density 0.054%

    No Known Activations