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

    Neuronpedia

    INDEX
    Explanations

    Addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    478
    -0.06
     anus
    -0.06
     uplift
    -0.06
    OLUTE
    -0.06
     offices
    -0.06
     مثال
    -0.06
     FORM
    -0.06
    quip
    -0.06
     matrices
    -0.06
    _oct
    -0.05
    POSITIVE LOGITS
    )tableView
    0.07
    ласти
    0.06
     jedis
    0.06
    ------↵↵
    0.06
     vi
    0.06
    (ArrayList
    0.06
    @↵
    0.06
    ستر
    0.06
    	class
    0.06
     �
    0.06
    Act Density 0.005%

    No Known Activations