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

    Neuronpedia

    INDEX
    Explanations

    references to monitoring or supervision activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    monitoring progress and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    envie
    -0.47
     lös
    -0.42
     kelebihan
    -0.41
     الشي
    -0.40
     spit
    -0.40
     erbjud
    -0.40
     incandescent
    -0.39
     Schre
    -0.39
     distilled
    -0.39
     spade
    -0.38
    POSITIVE LOGITS
    itored
    0.93
     monitored
    0.87
     monitor
    0.86
     Monitor
    0.75
    monitor
    0.72
     monitoring
    0.70
     MONITOR
    0.69
     monitors
    0.66
    Monitor
    0.66
     MONITORING
    0.65
    Act Density 0.012%

    No Known Activations