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

    Neuronpedia

    INDEX
    Explanations

    Introduction

    np_max-act · gemini-2.0-flash

    This neuron fires on document structuring tokens—section numbers, headings, and outline/bullet markers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _driver
    -0.06
     적
    -0.06
    enheim
    -0.06
    userManager
    -0.06
     sıcak
    -0.06
     Bloc
    -0.06
     Drivers
    -0.06
    uilt
    -0.06
    YSQL
    -0.06
    560
    -0.06
    POSITIVE LOGITS
     Tales
    0.08
     Ông
    0.06
     mientras
    0.06
    搜索
    0.06
    <::
    0.06
     Politico
    0.06
    ，又
    0.06
     قب
    0.06
     Regiment
    0.06
    �n
    0.06
    Act Density 0.015%

    No Known Activations