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

    Neuronpedia

    INDEX
    Explanations

    your personal information and credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     REPORTS
    0.87
     Reports
    0.78
    Reports
    0.77
     Talks
    0.74
     notícia
    0.73
    Calls
    0.68
     떨어
    0.67
     Announcements
    0.66
    Charts
    0.66
     reports
    0.66
    POSITIVE LOGITS
     username
    2.10
    username
    2.00
     Username
    1.98
    Username
    1.87
    用户名
    1.80
     usernames
    1.79
     login
    1.77
     credentials
    1.77
     PIN
    1.71
     password
    1.70
    Act Density 0.833%

    No Known Activations