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

    Neuronpedia

    INDEX
    Explanations

    preservation quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     duct
    -0.07
     termin
    -0.07
    墙
    -0.06
    ิ
    -0.06
    ustos
    -0.06
     treasurer
    -0.06
     arrangement
    -0.06
     Ms
    -0.06
     mayoría
    -0.06
    shots
    -0.06
    POSITIVE LOGITS
    無しさん
    0.06
    	glm
    0.06
    .skip
    0.06
     cust
    0.06
     repreh
    0.06
     StatefulWidget
    0.06
    trfs
    0.06
    posables
    0.06
    .);↵
    0.06
    τα
    0.06
    Act Density 0.088%

    No Known Activations