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

    Neuronpedia

    INDEX
    Explanations

    number one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     esos
    -0.07
    nets
    -0.07
    ient
    -0.07
    crast
    -0.06
     vis
    -0.06
     paed
    -0.06
    (training
    -0.06
    LTRB
    -0.06
    olicies
    -0.06
    ційних
    -0.06
    POSITIVE LOGITS
     Đầu
    0.07
     luận
    0.07
     الأول
    0.06
     toughest
    0.06
     düşün
    0.06
    Pokud
    0.06
    .MinValue
    0.06
     prime
    0.06
    .Fetch
    0.06
     primero
    0.06
    Act Density 0.006%

    No Known Activations