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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /G
    -0.07
     BOOK
    -0.06
     rational
    -0.06
     CBC
    -0.06
     ={
    -0.06
    angan
    -0.06
    /mail
    -0.06
    شور
    -0.06
     eagle
    -0.06
     _("
    -0.06
    POSITIVE LOGITS
     iceberg
    0.07
     договору
    0.06
     ظ
    0.06
     τά
    0.06
    .Sdk
    0.06
     welcoming
    0.06
     **/↵↵
    0.06
    uluğu
    0.06
    登場
    0.06
    Degrees
    0.06
    Act Density 0.000%

    No Known Activations