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

    Neuronpedia

    INDEX
    Explanations

    scientific evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    优化
    0.53
    连接
    0.52
     சேவை
    0.50
    手动
    0.50
     Geträn
    0.48
     स्टार्टअप
    0.47
     dành
    0.47
     интерфей
    0.45
     হবে
    0.45
     পোর্ট
    0.45
    POSITIVE LOGITS
     evidence
    1.13
     scientific
    1.11
    evidence
    0.99
     preuves
    0.99
    證據
    0.99
    证据
    0.97
     empir
    0.95
     научных
    0.93
     empirical
    0.92
     Evidence
    0.92
    Act Density 0.296%

    No Known Activations