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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     widely
    -0.06
    	transform
    -0.06
     Thurs
    -0.06
    -vers
    -0.06
     chồng
    -0.06
     society
    -0.06
    AWS
    -0.06
     clients
    -0.06
     generator
    -0.06
     receptors
    -0.06
    POSITIVE LOGITS
     with
    0.12
     With
    0.10
     WITH
    0.09
    with
    0.08
     avec
    0.08
    _with
    0.07
    Poster
    0.07
    unexpected
    0.07
    	with
    0.07
    With
    0.07
    Act Density 0.018%

    No Known Activations