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

    Neuronpedia

    INDEX
    Explanations

    client

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     produtos
    -0.08
     COLLECTION
    -0.06
    Types
    -0.06
     estimator
    -0.06
    through
    -0.06
    ocrates
    -0.06
    Balance
    -0.06
    engage
    -0.06
    Jordan
    -0.06
    desc
    -0.06
    POSITIVE LOGITS
     oč
    0.07
    .low
    0.07
    험
    0.07
    创新
    0.07
     işte
    0.06
    毕
    0.06
     трохи
    0.06
    .Failure
    0.06
    .failure
    0.06
    ▲
    0.06
    Act Density 0.006%

    No Known Activations