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

    Neuronpedia

    INDEX
    Explanations

    grafana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.94
    ли
    0.90
    لا
    0.81
    но
    0.77
    лили
    0.77
    лу
    0.75
    жи
    0.72
     راجسټریشن
    0.72
    ра
    0.71
    lüğü
    0.71
    POSITIVE LOGITS
    ong
    0.98
     It
    0.89
    ↵↵
    0.85
     (
    0.82
    ords
    0.81
    ant
    0.80
    ern
    0.79
    ',
    0.79
    al
    0.78
    ang
    0.78
    Act Density 0.002%

    No Known Activations