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

    Neuronpedia

    INDEX
    Explanations

    lightNatural light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рор
    0.39
    ্তার
    0.34
    嫦
    0.34
    ამდ
    0.33
    ớm
    0.33
    ুব্ধ
    0.33
    ទទ
    0.32
    gester
    0.32
    ccio
    0.32
    ندق
    0.31
    POSITIVE LOGITS
     light
    4.41
     Light
    4.13
    Light
    4.06
    light
    3.88
     LIGHT
    3.69
    LIGHT
    3.50
     लाइट
    3.41
     licht
    3.33
    ライト
    3.09
     свет
    2.98
    Act Density 0.186%

    No Known Activations