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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domicilio
    0.68
    ਰੀ
    0.67
    এক
    0.67
     chit
    0.66
    বিষয়
    0.66
     মধ্যে
    0.65
    ссия
    0.64
    अन्य
    0.64
     ene
    0.64
     недели
    0.63
    POSITIVE LOGITS
    c
    1.03
    ع
    0.86
    ش
    0.83
    b
    0.73
    ب
    0.72
    n
    0.69
    bass
    0.68
    ן
    0.67
    و
    0.67
    ্ড
    0.66
    Act Density 0.054%

    No Known Activations