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

    Neuronpedia

    INDEX
    Explanations

    Legal case numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     semaphore
    -0.07
     Pompe
    -0.07
     imposing
    -0.06
     시험
    -0.06
    /print
    -0.06
     onclick
    -0.06
     gym
    -0.06
    (points
    -0.06
    	print
    -0.06
     έ
    -0.06
    POSITIVE LOGITS
    390
    0.08
     Farms
    0.08
    ENDOR
    0.07
    360
    0.07
    LS
    0.07
    377
    0.07
     nhiêu
    0.07
    SG
    0.06
     Bloss
    0.06
    сім
    0.06
    Act Density 0.071%

    No Known Activations