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

    Neuronpedia

    INDEX
    Explanations

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     italic
    -0.08
    Enumerable
    -0.08
    Bonus
    -0.08
    Ini
    -0.08
    Buscar
    -0.07
     repudi
    -0.07
     Все
    -0.07
     বলতে
    -0.07
     tossed
    -0.07
    Todas
    -0.07
    POSITIVE LOGITS
     timeframe
    0.10
     generations
    0.09
     הד
    0.08
     modalities
    0.08
     regimes
    0.08
    -generation
    0.08
     Baghdad
    0.08
     परिस्थ
    0.08
     fandom
    0.08
    领域
    0.08
    Act Density 0.105%

    No Known Activations