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

    Neuronpedia

    INDEX
    Explanations

    Protocol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circuits
    -0.07
    eyes
    -0.07
    �
    -0.06
    ACION
    -0.06
     semantics
    -0.06
     �
    -0.06
    証
    -0.06
     clown
    -0.06
    acement
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    .Named
    0.07
     Andr
    0.07
    skin
    0.06
     spotting
    0.06
    -xl
    0.06
     Morg
    0.06
    $id
    0.06
    --[[
    0.06
    .Brand
    0.06
    ,output
    0.06
    Act Density 0.001%

    No Known Activations