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

    Neuronpedia

    INDEX
    Explanations

    kindly

    np_max-act · gemini-2.0-flash

    The neuron fires on polite acknowledgements of permission or offers—words like “kindly,” “allowed,” and “provided” that express gratitude or granted access.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hablar
    -0.06
    ampions
    -0.06
    ือก
    -0.06
    もう
    -0.06
    -IS
    -0.06
    _patch
    -0.06
     газ
    -0.06
    ヤ
    -0.06
    <quote
    -0.06
     зміни
    -0.06
    POSITIVE LOGITS
     kindly
    0.07
     -----------------------------------------------------------------------------↵
    0.07
     específ
    0.06
    andro
    0.06
     contato
    0.06
    Massage
    0.06
     searchText
    0.06
    (NO
    0.06
    Fecha
    0.06
     }//
    0.06
    Act Density 0.008%

    No Known Activations