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

    Neuronpedia

    INDEX
    Explanations

    IL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Null
    -0.07
    hook
    -0.06
     watchers
    -0.06
    рак
    -0.06
     sampler
    -0.06
    手を
    -0.06
    dealer
    -0.06
    麻
    -0.06
     sortable
    -0.06
     парт
    -0.06
    POSITIVE LOGITS
    	server
    0.06
    Arguments
    0.06
     stomach
    0.06
    "]),↵
    0.06
     Phân
    0.06
    (distance
    0.06
    शन
    0.06
     Gir
    0.06
    оді
    0.06
     jar
    0.06
    Act Density 0.632%

    No Known Activations