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

    Neuronpedia

    INDEX
    Explanations

    monitoring and tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    攘
    0.69
     оформления
    0.65
     বিভ
    0.62
     দ্বি
    0.62
    徕
    0.61
     permut
    0.61
     diffraction
    0.61
     प्लास्टिक
    0.60
    Grunge
    0.60
    zuge
    0.59
    POSITIVE LOGITS
     monitoring
    4.92
     Monitoring
    4.67
     monitor
    4.64
    Monitoring
    4.59
     Monitor
    4.38
     monitors
    4.36
    Monitor
    4.29
    monitoring
    4.23
     monitored
    4.15
    monitor
    4.11
    Act Density 0.461%

    No Known Activations