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

    Neuronpedia

    INDEX
    Explanations

    URL/web links

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens belonging to software license boilerplate (e.g. “License,” “licensing,” version numbers, legal‐URL fragments, and related terms) in code file headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	action
    -0.07
     siè
    -0.06
     Brid
    -0.06
    CE
    -0.06
    <W
    -0.06
     poč
    -0.06
     million
    -0.06
    sınız
    -0.06
     виг
    -0.06
     dispersion
    -0.06
    POSITIVE LOGITS
    SQLite
    0.06
    ContentAlignment
    0.06
     Централь
    0.06
     enlist
    0.06
     unheard
    0.06
    .decor
    0.06
     ECB
    0.06
     setPassword
    0.06
     nước
    0.06
     Community
    0.06
    Act Density 0.026%

    No Known Activations