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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragile
    -0.07
    .***
    -0.07
    Las
    -0.06
     písem
    -0.06
     Vulcan
    -0.06
     tradi
    -0.06
    �u
    -0.06
    ilies
    -0.06
     Franc
    -0.06
     Northwest
    -0.06
    POSITIVE LOGITS
    říklad
    0.07
    ิทย
    0.06
    就是
    0.06
    젤
    0.06
     ©
    0.06
    .grpc
    0.06
    (gulp
    0.06
    σφ
    0.06
    .initialize
    0.06
     permutation
    0.06
    Act Density 0.020%

    No Known Activations