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

    Neuronpedia

    INDEX
    Explanations

    important information and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beasts
    0.75
    fläche
    0.70
     coches
    0.69
     dissipated
    0.69
     squirrels
    0.68
    crever
    0.67
     vanished
    0.67
    bsen
    0.65
     sunk
    0.64
    ferred
    0.64
    POSITIVE LOGITS
     categorization
    0.89
     Information
    0.88
     Informat
    0.87
     Monitoring
    0.87
     Messaging
    0.86
     Notification
    0.86
     Highlights
    0.86
     Analytics
    0.84
     Reporting
    0.83
     Notifications
    0.83
    Act Density 0.001%

    No Known Activations