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

    Neuronpedia

    INDEX
    Explanations

    Enron forwarded emails

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لد
    -0.06
    .Footer
    -0.06
    지노
    -0.06
    ΟΚ
    -0.06
     �
    -0.06
    셨
    -0.06
     منتشر
    -0.06
     carts
    -0.06
    (KERN
    -0.06
    ダー
    -0.06
    POSITIVE LOGITS
     Experienced
    0.07
    )**
    0.07
    (wp
    0.07
     Этот
    0.06
     KH
    0.06
    nap
    0.06
    prepared
    0.06
     setResult
    0.06
    leyici
    0.06
    终
    0.06
    Act Density 0.003%

    No Known Activations