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

    Neuronpedia

    INDEX
    Explanations

    code snippets and text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nutrition
    -0.07
    نه
    -0.07
     Mal
    -0.07
     Chew
    -0.07
     observing
    -0.07
     Oro
    -0.07
    иров
    -0.07
    (G
    -0.07
     Male
    -0.07
     pig
    -0.06
    POSITIVE LOGITS
    	rm
    0.07
    大户
    0.07
    """↵
    0.07
    自带
    0.07
     urg
    0.07
    まとめ
    0.07
     mục
    0.06
    )$/
    0.06
    课堂
    0.06
    `).
    0.06
    Act Density 0.000%

    No Known Activations