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

    Neuronpedia

    INDEX
    Explanations

    code/document processing

    np_max-act · gemini-2.0-flash

    This neuron activates on polite solicitations and offers of assistance (e.g., “please provide…,” “I’d be happy to help,” “let me know”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ug
    -0.07
    اهی
    -0.07
     avi
    -0.06
     ratios
    -0.06
    ahi
    -0.06
    	project
    -0.06
    ION
    -0.06
    _TXT
    -0.06
    .getStatusCode
    -0.06
    ству
    -0.06
    POSITIVE LOGITS
     disappointed
    0.07
    .exc
    0.07
     runnable
    0.07
    ئيس
    0.06
     dě
    0.06
     работы
    0.06
    ンク
    0.06
     disappointing
    0.06
     weight
    0.06
    datum
    0.06
    Act Density 0.019%

    No Known Activations