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

    Neuronpedia

    INDEX
    Explanations

    `

    np_max-act · gemini-2.0-flash

    The neuron is picking up on Python code snippets—especially the fenced “```python” blocks and keywords like def —i.e. it signals when the text is a Python code fragment.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     quý
    -0.07
    _library
    -0.07
     departments
    -0.06
     пояс
    -0.06
    ็นว
    -0.06
    ISO
    -0.06
     ebp
    -0.06
    Sold
    -0.06
    ZN
    -0.06
    ابات
    -0.06
    POSITIVE LOGITS
    .assertTrue
    0.07
    usahaan
    0.07
     Rocks
    0.07
     Chunk
    0.06
     Fib
    0.06
     tether
    0.06
    등록
    0.06
    ETCH
    0.06
     bead
    0.06
    varchar
    0.06
    Act Density 0.037%

    No Known Activations