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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects Python dotted module or attribute references, such as import statements and “module.submodule” paths.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Arabs
    -0.07
    ội
    -0.06
    mb
    -0.06
     chỉnh
    -0.06
     μό
    -0.06
     накоп
    -0.06
    Ion
    -0.06
    来自
    -0.06
    	Buffer
    -0.06
     [](
    -0.06
    POSITIVE LOGITS
    Deployment
    0.07
     Companies
    0.07
    #/
    0.06
    633
    0.06
     کر
    0.06
     ambiente
    0.06
     खबर
    0.06
    .turn
    0.06
     Baby
    0.06
     blanco
    0.06
    Act Density 0.018%

    No Known Activations