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

    Neuronpedia

    INDEX
    Explanations

    import using

    np_max-act · gemini-2.0-flash

    This neuron detects programming code syntax—i.e. sequences of code tokens (like “using”, semicolons, braces, identifiers) rather than natural‐language text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     客
    -0.06
     ICC
    -0.06
     　　
    -0.06
     Rodr
    -0.06
    Kay
    -0.06
    ヤ
    -0.06
    ові
    -0.06
    Whole
    -0.06
     broth
    -0.06
    Labour
    -0.06
    POSITIVE LOGITS
     fits
    0.07
    )$_
    0.07
     Powers
    0.07
    quiring
    0.07
     bufio
    0.06
    .Element
    0.06
    _uint
    0.06
    WithData
    0.06
     AssetImage
    0.06
    DataSetChanged
    0.06
    Act Density 0.023%

    No Known Activations