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

    Neuronpedia

    INDEX
    Explanations

    you'd like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üllen
    0.68
    istiwa
    0.67
    convolution
    0.64
    ിക്കേണ്ട
    0.63
    ייס
    0.62
    Abort
    0.62
     चौथ
    0.62
     እንቅ
    0.62
    惶
    0.62
     sconf
    0.61
    POSITIVE LOGITS
     enjoy
    3.45
     enjoyed
    3.20
     enjoys
    3.17
     enjoying
    3.09
     Enjoy
    3.03
    enjoy
    2.95
    Enjoy
    2.95
     liked
    2.77
     enjoyment
    2.75
    喜欢
    2.61
    Act Density 1.051%

    No Known Activations