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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poil
    -0.07
     glazed
    -0.07
    睚
    -0.07
    焘
    -0.07
    茄子
    -0.07
     colour
    -0.06
    冔
    -0.06
     mb
    -0.06
    TX
    -0.06
     disregard
    -0.06
    POSITIVE LOGITS
    追求
    0.07
    itive
    0.07
    freq
    0.07
     Antarctic
    0.07
    ecessary
    0.07
     أيض
    0.07
     req
    0.06
     glob
    0.06
     política
    0.06
    	req
    0.06
    Act Density 0.443%

    No Known Activations