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

    Neuronpedia

    INDEX
    Explanations

    Authorization Bearer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العلوم
    0.42
    신기
    0.41
    PhysicalDevice
    0.41
    othelium
    0.40
     chimie
    0.40
     illusory
    0.39
     sonore
    0.39
     souris
    0.39
    磴
    0.39
    годні
    0.39
    POSITIVE LOGITS
     authentication
    1.37
    Authorization
    1.36
     Authorization
    1.35
     auth
    1.33
     authorization
    1.31
     Authentication
    1.30
    Authentication
    1.30
    認証
    1.22
     Auth
    1.20
    auth
    1.19
    Act Density 0.014%

    No Known Activations