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

    Neuronpedia

    INDEX
    Explanations

    technical and professional terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑛
    3.23
    𝑡
    3.02
    Р
    3.01
    𝑟
    2.96
     amely
    2.84
    𝑦
    2.80
     писатель
    2.75
     ninguno
    2.73
     ১৫
    2.72
    Ö
    2.70
    POSITIVE LOGITS
    et
    3.95
    es
    3.19
    ات
    3.12
    ನ್ನು
    2.97
    ed
    2.97
    ة
    2.97
    al
    2.89
    de
    2.89
    ે
    2.87
    ์
    2.76
    Act Density 0.162%

    No Known Activations