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

    Neuronpedia

    INDEX
    Explanations

    long listing format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нина
    0.46
     അവസ്ഥ
    0.44
     Ман
    0.44
     достав
    0.43
    ATI
    0.43
     కనిప
    0.43
     распро
    0.43
    餐
    0.43
    4
    0.42
    ホ
    0.42
    POSITIVE LOGITS
     توڑ
    0.46
     sports
    0.46
     music
    0.45
     liturgical
    0.44
     diffe
    0.44
     unilateral
    0.44
     இசை
    0.43
     muziek
    0.43
    ပြု
    0.43
    ၍
    0.43
    Act Density 0.001%

    No Known Activations