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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nodes
    -0.08
    	component
    -0.07
     diese
    -0.07
    name
    -0.07
    잼
    -0.07
    рен
    -0.07
    CASE
    -0.06
     شركة
    -0.06
     cig
    -0.06
    real
    -0.06
    POSITIVE LOGITS
    𝘙
    0.07
    .Agent
    0.07
    _AI
    0.07
    _DEBUG
    0.07
    צדק
    0.07
    أكل
    0.06
    ++)↵
    0.06
    "}},↵
    0.06
    ']]
    0.06
    ;")↵
    0.06
    Act Density 0.003%

    No Known Activations