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

    Neuronpedia

    INDEX
    Explanations

    access control and authorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لگ
    0.46
     sus
    0.40
    Youth
    0.40
    ករណ៍
    0.39
     काउंटर
    0.39
     Youth
    0.39
    絡
    0.39
    Sus
    0.38
     promov
    0.38
     fawn
    0.38
    POSITIVE LOGITS
     Roles
    0.64
     roles
    0.61
    roles
    0.55
    Roles
    0.55
     ROLE
    0.55
     role
    0.47
     Authorization
    0.46
    資源
    0.46
     authorization
    0.45
    Role
    0.45
    Act Density 0.005%

    No Known Activations