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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    い
    0.62
    า
    0.61
    ﻮ
    0.57
     त्यानंतर
    0.55
     sebagainya
    0.55
    ia
    0.54
    okban
    0.54
     Saturday
    0.51
    ו
    0.50
    on
    0.50
    POSITIVE LOGITS
    ।
    0.81
    ។
    0.80
     as
    0.78
    ٹ
    0.76
     in
    0.73
    ق
    0.72
    ۔
    0.71
    گ
    0.70
     for
    0.69
    ن
    0.68
    Act Density 0.103%

    No Known Activations