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

    Neuronpedia

    INDEX
    Explanations

    diagonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">{{$
    -0.07
    hands
    -0.07
    =".$_
    -0.07
     Bert
    -0.07
    '>$
    -0.06
     movies
    -0.06
     Walters
    -0.06
     sprintf
    -0.06
    bero
    -0.06
     remix
    -0.06
    POSITIVE LOGITS
     diagonal
    0.15
    agonal
    0.09
     diagon
    0.09
    diag
    0.07
     decentralized
    0.07
    ederal
    0.07
    .localization
    0.06
    idlo
    0.06
     decimal
    0.06
     diag
    0.06
    Act Density 0.001%

    No Known Activations