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

    Neuronpedia

    INDEX
    Explanations

    countries and programming languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     téléphone
    0.98
     pembuatan
    0.92
    ńczy
    0.91
     teléfono
    0.90
     شهرستان
    0.88
    flora
    0.87
     powiat
    0.87
     klanten
    0.86
     criada
    0.86
     così
    0.85
    POSITIVE LOGITS
    Des
    0.80
     Des
    0.73
    いずれ
    0.70
    Raz
    0.67
    Gang
    0.67
    mandu
    0.67
    lastKey
    0.62
     अनु
    0.62
    Margaret
    0.62
    με
    0.60
    Act Density 0.291%

    No Known Activations