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

    Neuronpedia

    INDEX
    Explanations

    German reflexive pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.09
    其他
    0.91
    ü
    0.86
    ী
    0.86
    re
    0.81
    G
    0.80
    ről
    0.78
    B
    0.78
    mh
    0.78
    tm
    0.77
    POSITIVE LOGITS
     Partai
    0.73
    ot
    0.71
    д
    0.70
    ٹ
    0.66
     saluran
    0.66
    az
    0.65
    acijos
    0.65
    加え
    0.65
    지
    0.64
    部の
    0.64
    Act Density 0.041%

    No Known Activations