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

    Neuronpedia

    INDEX
    Explanations

    parse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .progressBar
    -0.07
    쿠
    -0.06
     //<
    -0.06
    ENDER
    -0.06
    adu
    -0.06
     productName
    -0.06
    _sizes
    -0.06
    _author
    -0.06
     brushing
    -0.06
    pool
    -0.06
    POSITIVE LOGITS
     orta
    0.07
    -buttons
    0.07
     کل
    0.07
     оди
    0.06
    achusetts
    0.06
    -CP
    0.06
     tổng
    0.06
    erral
    0.06
     характ
    0.06
    抜
    0.06
    Act Density 0.003%

    No Known Activations