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

    Neuronpedia

    INDEX
    Explanations

    satellite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     legends
    -0.07
     Manager
    -0.07
     broad
    -0.07
    装
    -0.07
     Client
    -0.07
     sections
    -0.07
     opponent
    -0.06
     Testing
    -0.06
     drivers
    -0.06
    _number
    -0.06
    POSITIVE LOGITS
     dit
    0.07
     paralle
    0.07
    SAT
    0.07
     brittle
    0.07
     ET
    0.06
    sat
    0.06
     tí
    0.06
     Satellite
    0.06
    .herokuapp
    0.06
    hdl
    0.06
    Act Density 0.003%

    No Known Activations