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
    층
    -0.07
     nedir
    -0.06
     hroz
    -0.06
     ένας
    -0.06
     öner
    -0.06
    زارش
    -0.06
    ouncer
    -0.06
    architecture
    -0.06
     próxima
    -0.06
     imp
    -0.06
    POSITIVE LOGITS
    bt
    0.07
     کنید
    0.07
    票
    0.07
    ีอ
    0.06
    stras
    0.06
    �제
    0.06
    你
    0.06
    appa
    0.06
    xCC
    0.06
    BT
    0.06
    Act Density 0.001%

    No Known Activations