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

    Neuronpedia

    INDEX
    Explanations

    sorted lists and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ძალი
    0.47
    ﻧ
    0.46
     مذہ
    0.43
     язы
    0.43
    闹
    0.43
     pelaku
    0.41
    贬
    0.41
     Propagation
    0.39
     пато
    0.39
     lucu
    0.39
    POSITIVE LOGITS
    Sorted
    0.64
     sorted
    0.59
     Sorted
    0.59
     range
    0.55
    sorted
    0.54
     gaps
    0.52
    range
    0.47
     median
    0.46
    ılmış
    0.42
     gap
    0.42
    Act Density 0.110%

    No Known Activations