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

    Neuronpedia

    INDEX
    Explanations

    bipartite matching/graphs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forecast
    -0.10
     forecasts
    -0.09
     spelled
    -0.09
     tweets
    -0.08
     tweet
    -0.08
    Forecast
    -0.08
    Frequently
    -0.07
     spelling
    -0.07
     Forecast
    -0.07
    shots
    -0.07
    POSITIVE LOGITS
     bride
    0.09
     namoro
    0.09
     tendon
    0.09
     sexuelle
    0.08
     স্ত্রী
    0.08
     নারী
    0.08
     காத
    0.08
     മത്സ
    0.08
     মাছ
    0.08
     মহিলা
    0.08
    Act Density 0.003%

    No Known Activations