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

    Neuronpedia

    INDEX
    Explanations

    substantial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Grab
    -0.06
    胆固
    -0.06
     Stap
    -0.06
    (cart
    -0.06
    Attachments
    -0.06
    尤其
    -0.06
     Griff
    -0.06
     bild
    -0.06
    	ASSERT
    -0.06
     mentoring
    -0.06
    POSITIVE LOGITS
    宝妈
    0.07
    Ｚ
    0.07
    isky
    0.07
    Л
    0.06
    _trials
    0.06
    ц
    0.06
    _quantity
    0.06
    estic
    0.06
    促进
    0.06
    _columns
    0.06
    Act Density 0.002%

    No Known Activations