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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash

    The neuron fires on masked hyperlink placeholders—tokens like “login,” “view,” and “URL” (often inside brackets) that signal a hidden or “click-to-reveal” link.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    entries related to job descriptions specifically for content creation and project requirements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Des
    -0.07
     pBuffer
    -0.07
    	auto
    -0.06
    าประ
    -0.06
     depot
    -0.06
     REMOVE
    -0.06
     brigade
    -0.06
    Thanks
    -0.06
    tics
    -0.06
    ade
    -0.06
    POSITIVE LOGITS
     nghiên
    0.06
    gis
    0.06
     ảnh
    0.06
     على
    0.06
    ło
    0.06
    .ide
    0.06
    нед
    0.06
     komplex
    0.06
     occasions
    0.06
    iquid
    0.06
    Act Density 0.003%

    No Known Activations