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

    Neuronpedia

    INDEX
    Explanations

    family relationships and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ります
    0.62
    iyoruz
    0.59
    判断
    0.57
    క్కడ
    0.55
    flake
    0.54
    場合
    0.54
     если
    0.54
    ।'
    0.52
    '></
    0.51
    焼
    0.51
    POSITIVE LOGITS
    ،
    1.00
     extraordinaire
    0.92
    ,
    0.89
     nommé
    0.78
     bernama
    0.77
     namely
    0.77
     Michael
    0.76
     Charles
    0.76
     named
    0.73
     Richard
    0.73
    Act Density 0.024%

    No Known Activations