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

    Neuronpedia

    INDEX
    Explanations

    numbers and Bengali numerals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٥
    0.69
     असा
    0.68
     fifth
    0.67
    Ỗ
    0.66
     dico
    0.65
     ५
    0.64
    irmi
    0.64
     五
    0.64
    inhard
    0.64
     Fan
    0.63
    POSITIVE LOGITS
     twelve
    0.79
     ১২
    0.77
    Twelve
    0.75
    ১৩
    0.72
    ১২
    0.71
     ১৩
    0.69
    Eleven
    0.68
     १३
    0.67
     Lattice
    0.66
     ११
    0.66
    Act Density 0.067%

    No Known Activations