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

    Neuronpedia

    INDEX
    Explanations

    notifications, alerts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legalized
    -0.07
     chrono
    -0.07
     crush
    -0.07
    �
    -0.07
    晶
    -0.07
     sustainable
    -0.07
     plastic
    -0.07
     djel
    -0.07
     zák
    -0.07
    Rules
    -0.07
    POSITIVE LOGITS
     уведом
    0.16
     alerts
    0.16
     alerted
    0.16
    通知
    0.16
    报警
    0.16
     notifying
    0.15
     notification
    0.15
     notific
    0.14
    Alerts
    0.14
     notifications
    0.14
    Act Density 0.007%

    No Known Activations