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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inicio
    -0.07
     relinqu
    -0.07
     NCAA
    -0.07
    Rs
    -0.06
    令
    -0.06
    นส
    -0.06
     ['#
    -0.06
    Combine
    -0.06
     declares
    -0.06
    Notice
    -0.06
    POSITIVE LOGITS
    rai
    0.06
    687
    0.06
    Owner
    0.06
     และ
    0.06
     商品
    0.06
     Fitness
    0.06
     реб
    0.06
    .saved
    0.06
    {
↵
    0.06
    \Resource
    0.06
    Act Density 0.012%

    No Known Activations