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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    5
    -0.08
    4
    -0.07
    3
    -0.07
    �藏
    -0.06
     womens
    -0.06
     Doğum
    -0.06
    getRow
    -0.06
    ２
    -0.06
     Feet
    -0.06
     day
    -0.06
    POSITIVE LOGITS
    uset
    0.08
     mailbox
    0.07
    уск
    0.07
    Namespace
    0.07
    σι
    0.07
    annie
    0.07
     Npgsql
    0.07
    ACHE
    0.07
    нет
    0.07
    ورش
    0.06
    Act Density 0.005%

    No Known Activations