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

    Neuronpedia

    INDEX
    Explanations

    early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bounds
    -0.07
     sắp
    -0.07
    -known
    -0.07
     altri
    -0.07
    鮮
    -0.07
     increases
    -0.07
     known
    -0.07
     importante
    -0.07
     Kore
    -0.07
     국가
    -0.07
    POSITIVE LOGITS
     millennia
    0.07
     sublicense
    0.06
    완
    0.06
    ністю
    0.06
    يار
    0.06
    ินท
    0.06
    acidad
    0.06
    个人
    0.06
    ваются
    0.06
    Specify
    0.06
    Act Density 0.035%

    No Known Activations