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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     malls
    -0.09
     Rockstar
    -0.09
     gasoline
    -0.09
     nightlife
    -0.08
     loneliness
    -0.08
     viral
    -0.08
     Viral
    -0.08
    viral
    -0.08
    Mysql
    -0.08
     menschen
    -0.08
    POSITIVE LOGITS
     handicap
    0.09
     comparator
    0.09
     प्रतियोग
    0.09
     recorder
    0.09
    Configurator
    0.08
     Hague
    0.08
    Benchmark
    0.08
    Recorder
    0.08
     Benchmark
    0.08
    ITU
    0.08
    Act Density 0.013%

    No Known Activations