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

    Neuronpedia

    INDEX
    Explanations

    beginning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    square
    -0.06
     pNode
    -0.06
     nhẹ
    -0.06
     Lung
    -0.06
     margins
    -0.06
     square
    -0.06
    алась
    -0.06
    	handle
    -0.06
    ODE
    -0.06
    >(
    -0.06
    POSITIVE LOGITS
    initely
    0.07
    shares
    0.06
    은
    0.06
    tps
    0.06
    озем
    0.06
    [R
    0.06
    poser
    0.06
    чення
    0.06
    lbrakk
    0.06
    phia
    0.06
    Act Density 0.135%

    No Known Activations