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

    Neuronpedia

    INDEX
    Explanations

    same or similar wording

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preprocess
    0.46
     alphanumeric
    0.43
     obeys
    0.42
     پیک
    0.41
     preprocessing
    0.40
     heuristic
    0.40
     computational
    0.40
     generate
    0.39
     processors
    0.39
     tensor
    0.38
    POSITIVE LOGITS
    ua
    0.52
    sama
    0.50
    同じ
    0.50
    same
    0.48
     इसी
    0.48
    Ibid
    0.47
     Sama
    0.47
    ena
    0.47
     जास्त
    0.46
     same
    0.46
    Act Density 0.002%

    No Known Activations