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

    Neuronpedia

    INDEX
    Explanations

    server data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -thirds
    -0.09
     horny
    -0.08
    .sky
    -0.08
    -ter
    -0.08
     Coastal
    -0.08
    早餐
    -0.08
     Carnegie
    -0.08
     inciso
    -0.08
     разам
    -0.08
    -sk
    -0.08
    POSITIVE LOGITS
    监
    0.13
    監
    0.13
     monitoring
    0.12
     uptime
    0.12
     monitored
    0.12
    Monitoring
    0.12
    性能
    0.11
     monitor
    0.11
     Monitoring
    0.11
    Monitor
    0.11
    Act Density 0.023%

    No Known Activations