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

    Neuronpedia

    INDEX
    Explanations

    polys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    working
    -0.07
    casting
    -0.06
     EDGE
    -0.06
     sama
    -0.06
    icode
    -0.06
    icc
    -0.06
     wrapper
    -0.06
    aret
    -0.06
    itan
    -0.06
     GPU
    -0.06
    POSITIVE LOGITS
     polys
    0.15
    .Strings
    0.08
    。不过
    0.07
     as
    0.07
     envoy
    0.06
     birisi
    0.06
    Архів
    0.06
     Qty
    0.06
    ....↵
    0.06
    unist
    0.06
    Act Density 0.001%

    No Known Activations