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

    Neuronpedia

    INDEX
    Explanations

    nationalities and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unes
    0.70
     Passover
    0.69
     যাঁ
    0.67
    hasOwnProperty
    0.66
     word
    0.66
    មនុស្ស
    0.64
    সংঘ
    0.64
     نړۍ
    0.63
     Weierstrass
    0.63
     continents
    0.63
    POSITIVE LOGITS
     българ
    2.23
     한국
    1.96
    日本の
    1.96
     우리나라
    1.95
     Ghanaian
    1.93
     Filipino
    1.92
     brasileira
    1.91
     Malaysian
    1.90
     বাংলাদেশি
    1.90
     norske
    1.89
    Act Density 0.641%

    No Known Activations