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

    Neuronpedia

    INDEX
    Explanations

    rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("**
    -0.07
    PropertyDescriptor
    -0.07
     приход
    -0.07
     πά
    -0.06
    省
    -0.06
     cellar
    -0.06
    ('//*[@
    -0.06
    分析
    -0.06
    ihn
    -0.06
     epsilon
    -0.06
    POSITIVE LOGITS
     hızla
    0.07
     나
    0.07
    TEXT
    0.07
    .cgColor
    0.06
    	Double
    0.06
     cough
    0.06
    GameManager
    0.06
    png
    0.06
    .Summary
    0.06
    onder
    0.06
    Act Density 0.009%

    No Known Activations