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

    Neuronpedia

    INDEX
    Explanations

    actions followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    エコ
    0.49
     ویب
    0.46
    baik
    0.46
    ૧
    0.45
    baiki
    0.43
     त्यांनी
    0.42
    وک
    0.42
    com
    0.42
    一年
    0.42
     lançamento
    0.41
    POSITIVE LOGITS
     traversal
    0.58
     müş
    0.48
     tubes
    0.47
     whiskey
    0.45
     diodes
    0.44
     modul
    0.44
     traverses
    0.44
    టర్‌
    0.44
     ক্লা
    0.44
    يقة
    0.43
    Act Density 0.005%

    No Known Activations