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

    Neuronpedia

    INDEX
    Explanations

    patent methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क्षेप
    0.47
    iless
    0.46
    僭
    0.46
    湁
    0.46
    되고
    0.45
    GlobalSection
    0.45
     ആണ്
    0.45
    天赋
    0.45
    सद
    0.44
    abhavena
    0.44
    POSITIVE LOGITS
     patents
    0.53
     patent
    0.52
     P
    0.50
     inventors
    0.48
     D
    0.46
     Patent
    0.45
     training
    0.43
     N
    0.42
     W
    0.42
     lumber
    0.41
    Act Density 0.000%

    No Known Activations