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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ゅ
    -0.07
    cludes
    -0.07
     López
    -0.07
    Jack
    -0.07
    ψη
    -0.07
     Tehran
    -0.07
     İngilizce
    -0.07
     tướng
    -0.06
     mosque
    -0.06
    Ž
    -0.06
    POSITIVE LOGITS
    probante
    0.06
    .orders
    0.06
     افر
    0.06
     uphold
    0.06
    acea
    0.06
    .setRequest
    0.06
    $values
    0.06
     bal
    0.06
    认
    0.06
    .pay
    0.06
    Act Density 0.013%

    No Known Activations