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

    Neuronpedia

    INDEX
    Explanations

    User privileges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haal
    -0.08
     trendy
    -0.08
    呈
    -0.08
     armon
    -0.08
     steadily
    -0.08
     commercially
    -0.08
     taza
    -0.08
     presentar
    -0.08
     presentamos
    -0.08
    etooth
    -0.08
    POSITIVE LOGITS
     privilegi
    0.12
    权限
    0.12
     bevoegd
    0.12
     privileges
    0.12
     administrador
    0.12
    管理员
    0.12
     관리자
    0.12
     privileged
    0.11
    /admin
    0.11
     administrator
    0.11
    Act Density 0.019%

    No Known Activations