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

    Neuronpedia

    INDEX
    Explanations

    Authentication/MFA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dish
    -0.09
     NOI
    -0.08
     sibi
    -0.08
     deity
    -0.08
     soci
    -0.08
    社会主义
    -0.08
     ਛ
    -0.08
     szer
    -0.07
    �
    -0.07
     recorrer
    -0.07
    POSITIVE LOGITS
     protects
    0.10
     wherever
    0.09
     recommended
    0.08
    增强
    0.08
     Wherever
    0.08
    、防
    0.08
     phishing
    0.08
     minimizes
    0.08
    Наст
    0.08
     passwords
    0.08
    Act Density 0.005%

    No Known Activations