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

    Neuronpedia

    INDEX
    Explanations

    language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sectional
    -0.07
     Metric
    -0.07
     Braves
    -0.07
    occupation
    -0.07
    豫
    -0.07
    二十四
    -0.07
     antagonist
    -0.07
    unk
    -0.07
     progressDialog
    -0.07
    bulk
    -0.07
    POSITIVE LOGITS
    🏧
    0.07
    /themes
    0.06
    也是
    0.06
    📍
    0.06
    开着
    0.06
    总共
    0.06
    (ts
    0.06
     %{
    0.06
     vern
    0.06
    '].
    0.06
    Act Density 0.033%

    No Known Activations