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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Christus
    -0.07
     возраст
    -0.07
    Laura
    -0.07
     максимально
    -0.07
    Voilà
    -0.07
     marketing
    -0.07
     raspberry
    -0.07
     મુજબ
    -0.07
     licensed
    -0.07
    销售
    -0.07
    POSITIVE LOGITS
     (>
    0.10
     nécessite
    0.09
     kaç
    0.09
    requ
    0.08
     requiring
    0.08
    場合
    0.08
    تر
    0.08
    inar
    0.08
     membutuhkan
    0.08
     требует
    0.08
    Act Density 0.079%

    No Known Activations