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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Don
    -0.07
    欣喜
    -0.07
     fanatic
    -0.07
    肪
    -0.07
     grayscale
    -0.07
     khách
    -0.07
     sublicense
    -0.07
     délai
    -0.07
    	username
    -0.07
     Neville
    -0.07
    POSITIVE LOGITS
    述职
    0.07
    只是为了
    0.07
     opp
    0.06
    𐌺
    0.06
     pressure
    0.06
    离开了
    0.06
    学术
    0.06
    مواجه
    0.06
    >/<
    0.06
    -destruct
    0.06
    Act Density 0.222%

    No Known Activations