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

    Neuronpedia

    INDEX
    Explanations

    Microscopic analysis/lab experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     courses
    -0.08
    (dict
    -0.08
    985
    -0.07
     geopolitical
    -0.07
     resonance
    -0.07
    ейтинг
    -0.07
    ERP
    -0.07
     regrets
    -0.07
     revenue
    -0.07
     receptions
    -0.07
    POSITIVE LOGITS
    刷
    0.08
    �
    0.08
    ifanya
    0.08
     удалить
    0.08
     wür
    0.08
     pedestrian
    0.08
    /sample
    0.08
     Visualization
    0.08
    Paste
    0.08
     Vorte
    0.08
    Act Density 0.003%

    No Known Activations