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

    Neuronpedia

    INDEX
    Explanations

    user accounts and logins

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the login process—especially tokens like “login” or “login page” in a user-authentication context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Reduce
    -0.08
     worst
    -0.07
    (site
    -0.07
    ’est
    -0.07
     社
    -0.07
    (circle
    -0.06
    _walk
    -0.06
     Wander
    -0.06
    체
    -0.06
    яз
    -0.06
    POSITIVE LOGITS
    }'",
    0.06
     businessmen
    0.06
    /$',
    0.06
     ​​
    0.06
    贵
    0.06
    Identifier
    0.06
     biliyor
    0.06
    .annotations
    0.06
     '}';↵
    0.06
    έργ
    0.06
    Act Density 0.015%

    No Known Activations