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

    Neuronpedia

    INDEX
    Explanations

    tiered approach, component-based architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.80
    าก
    0.75
     niemals
    0.75
     tampoco
    0.74
    ायक
    0.73
     C
    0.71
     smelled
    0.70
    og
    0.67
    t
    0.67
    าน
    0.66
    POSITIVE LOGITS
     thức
    1.01
     পদ্ধতিতে
    0.93
    Tại
    0.88
    יות
    0.86
    ೇಶ್
    0.86
    рель
    0.85
    的是
    0.83
    ট্র
    0.83
    cG
    0.83
    ৪
    0.82
    Act Density 0.770%

    No Known Activations