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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंत
    0.89
    щите
    0.74
     freest
    0.73
    itative
    0.73
    ות
    0.73
     carbone
    0.72
    তাবাদী
    0.69
    itati
    0.67
    你看
    0.67
    borderRadius
    0.67
    POSITIVE LOGITS
     사항
    0.96
     stojí
    0.90
    從
    0.89
     जमाने
    0.83
    jado
    0.81
    stash
    0.80
     mäng
    0.79
    ifrån
    0.79
    िल्‍ली
    0.78
    ق
    0.78
    Act Density 0.038%

    No Known Activations