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

    Neuronpedia

    INDEX
    Explanations

    Collegiate titles and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ឡើង
    0.43
    پے
    0.41
     行っ
    0.41
     행
    0.40
     হোট
    0.39
    浮
    0.39
    𝙥
    0.38
    ിയെ
    0.38
     Highlight
    0.38
    tric
    0.38
    POSITIVE LOGITS
    Col
    0.54
     TM
    0.49
     col
    0.49
    Coll
    0.48
     Tail
    0.48
     tail
    0.48
    DM
    0.48
    col
    0.48
     Colt
    0.48
     DM
    0.46
    Act Density 0.000%

    No Known Activations