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

    Neuronpedia

    INDEX
    Explanations

    multilingual and non-alphanumeric symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     경기
    0.48
     Exodus
    0.47
     služby
    0.45
     Businessman
    0.43
     City
    0.43
     Brothers
    0.43
     ப்ர
    0.43
    iduría
    0.42
    kker
    0.42
    örper
    0.42
    POSITIVE LOGITS
     نیز
    0.58
    ﺿ
    0.50
     capire
    0.49
     semplic
    0.49
    및
    0.48
    ږ
    0.47
    ﺕ
    0.47
    খ
    0.47
    ږي
    0.46
    及び
    0.45
    Act Density 0.001%

    No Known Activations