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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash

    The neuron activates on URL tokens (e.g. “http://…”)—i.e. it detects web links in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .mob
    -0.07
     Tabs
    -0.07
     हज
    -0.07
     Meng
    -0.06
    ;">
↵
    -0.06
     valign
    -0.06
     Ally
    -0.06
     behand
    -0.06
    	UObject
    -0.06
     After
    -0.06
    POSITIVE LOGITS
    만원입니다
    0.07
    /content
    0.06
    rust
    0.06
    \F
    0.06
    ıydı
    0.06
    cht
    0.06
    DOI
    0.06
    teenth
    0.06
     Sustainability
    0.06
     سیستم
    0.06
    Act Density 0.011%

    No Known Activations