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

    Neuronpedia

    INDEX
    Explanations

    C/C++ operator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .get
    -0.06
    ้าของ
    -0.06
     keyboards
    -0.06
    .Secret
    -0.06
    (div
    -0.06
    atasets
    -0.06
     controlling
    -0.06
     نبود
    -0.06
    (models
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ++];↵
    0.07
    ++);↵
    0.07
    �
    0.07
    ++↵
    0.07
    ++]
    0.07
    prus
    0.07
    )++;↵
    0.07
    638
    0.07
     Utils
    0.07
    ++
    0.07
    Act Density 0.003%

    No Known Activations