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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    This neuron activates on segments of filesystem paths (especially model or resource file paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     presum
    -0.07
    _market
    -0.06
     علی
    -0.06
     Celebrity
    -0.06
    Ton
    -0.06
     slender
    -0.06
    FDA
    -0.06
     voir
    -0.06
    enis
    -0.06
    _Tree
    -0.06
    POSITIVE LOGITS
    tableFuture
    0.07
    quence
    0.07
     нашей
    0.06
    prev
    0.06
    センター
    0.06
     Glasses
    0.06
    티
    0.06
    dio
    0.06
     генера
    0.06
     의해
    0.06
    Act Density 0.018%

    No Known Activations