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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Doctrine
    -0.07
     mắt
    -0.07
     있어서
    -0.06
    زی
    -0.06
    woocommerce
    -0.06
     Earth
    -0.06
     Poh
    -0.06
     Thế
    -0.06
    ascular
    -0.06
    -earth
    -0.06
    POSITIVE LOGITS
    OMETRY
    0.08
    搜索
    0.07
    ethereum
    0.07
     أحمد
    0.06
    metics
    0.06
     benöt
    0.06
    Allow
    0.06
    ,j
    0.06
     MAGIC
    0.06
     imperative
    0.06
    Act Density 0.001%

    No Known Activations