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

    Neuronpedia

    INDEX
    Explanations

    monitoring performance and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     topologically
    0.42
     sympat
    0.40
    slüman
    0.40
    fach
    0.39
    iclopedia
    0.38
     ontological
    0.38
     inhomogeneous
    0.38
    ផុត
    0.37
     inhomogeneities
    0.37
     oggetti
    0.37
    POSITIVE LOGITS
     monitoring
    1.05
     Monitoring
    0.96
    Monitoring
    0.92
    monitoring
    0.89
     metrics
    0.89
     monitor
    0.86
     KPIs
    0.86
     dashboards
    0.86
     monitored
    0.85
     Metrics
    0.81
    Act Density 0.275%

    No Known Activations