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

    Neuronpedia

    INDEX
    Explanations

    list of keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Buster
    0.67
     Asha
    0.59
    werk
    0.58
     وسائل
    0.57
     tapas
    0.56
    íd
    0.55
    neider
    0.55
    kamer
    0.55
    förm
    0.55
    nahmen
    0.55
    POSITIVE LOGITS
     keywords
    1.10
    as
    0.93
    on
    0.93
    and
    0.93
    Keywords
    0.92
    at
    0.90
    ای
    0.90
     Keywords
    0.89
     keyword
    0.89
    К
    0.88
    Act Density 0.023%

    No Known Activations