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

    Neuronpedia

    INDEX
    Explanations

    html attributes and xpath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🍡
    0.44
     saranno
    0.40
     світі
    0.40
     بدء
    0.39
     ለ
    0.38
     допомо
    0.38
     sommes
    0.38
     Cray
    0.38
    🏺
    0.38
    這次
    0.38
    POSITIVE LOGITS
    aria
    0.55
     role
    0.48
     tabindex
    0.47
    undefined
    0.47
    ARIA
    0.47
    tab
    0.46
    xpath
    0.45
     roles
    0.45
    arian
    0.45
    role
    0.44
    Act Density 0.002%

    No Known Activations