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

    Neuronpedia

    INDEX
    Explanations

    User input or code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ផ្
    0.73
    ភ្ជាប់
    0.72
    pes
    0.69
     Millet
    0.69
    peas
    0.69
    jer
    0.69
    өт
    0.69
    hop
    0.69
     кол
    0.68
    }}=$
    0.68
    POSITIVE LOGITS
     RETURN
    0.67
     aigu
    0.67
    RETURN
    0.64
     ডেস্ক
    0.63
     سرمایہ
    0.63
     স্যাম
    0.63
     देयर
    0.63
     There
    0.62
     Obviously
    0.61
    用户信息
    0.61
    Act Density 0.007%

    No Known Activations