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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     qr
    -0.07
    οκ
    -0.07
    .Xtra
    -0.07
    STEP
    -0.07
    outputs
    -0.06
     filetype
    -0.06
    jte
    -0.06
    VERT
    -0.06
     دوربین
    -0.06
    .optimize
    -0.06
    POSITIVE LOGITS
    \Config
    0.07
     guess
    0.06
    Layer
    0.06
     Suite
    0.06
     associative
    0.06
     Casey
    0.06
     aftermath
    0.06
     Poster
    0.06
    aginator
    0.06
    -parameter
    0.06
    Act Density 0.019%

    No Known Activations