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

    Neuronpedia

    INDEX
    Explanations

    documentclass article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SYSTEMS
    0.67
     বাম
    0.62
     технологии
    0.62
    ively
    0.61
     դ
    0.58
    を使用
    0.57
    的技术
    0.57
     ব্যবহার
    0.57
     ယ
    0.57
    の使用
    0.57
    POSITIVE LOGITS
    in
    1.13
    ad
    0.98
    c
    0.88
    z
    0.82
    n
    0.82
    s
    0.81
    x
    0.78
    न
    0.78
    ↵
    0.77
    r
    0.76
    Act Density 0.001%

    No Known Activations