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

    Neuronpedia

    INDEX
    Explanations

    cut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Action
    -0.06
    	fp
    -0.06
     poem
    -0.06
    ENTRY
    -0.06
     HttpMethod
    -0.06
    	pos
    -0.06
    selector
    -0.06
    Ð
    -0.06
    	GameObject
    -0.06
     io
    -0.06
    POSITIVE LOGITS
     EDUC
    0.08
    -www
    0.07
    кан
    0.06
    -auth
    0.06
     Exhibition
    0.06
    abl
    0.06
    alloc
    0.06
     Coupons
    0.06
    していた
    0.06
     unsus
    0.06
    Act Density 0.046%

    No Known Activations