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
    nickname
    -0.08
     Tart
    -0.07
    Scope
    -0.07
    .RequestBody
    -0.06
    /MM
    -0.06
    .ActionListener
    -0.06
    法国
    -0.06
     marty
    -0.06
     GetData
    -0.06
     Ply
    -0.06
    POSITIVE LOGITS
    нев
    0.06
    router
    0.06
     createState
    0.06
    هن
    0.06
     absolutely
    0.06
    ueva
    0.06
    ่า
    0.06
     fuera
    0.06
    ulması
    0.06
     il
    0.06
    Act Density 0.009%

    No Known Activations