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

    Neuronpedia

    INDEX
    Explanations

    thank

    np_max-act · gemini-2.0-flash

    The neuron fires on courteous, formulaic expressions of thanks, gratitude, or polite greetings in formal addresses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ^^
    -0.07
    olics
    -0.06
    цион
    -0.06
    Las
    -0.06
    vasion
    -0.06
    خاص
    -0.06
    vron
    -0.06
    NUM
    -0.06
    adge
    -0.06
    _sec
    -0.06
    POSITIVE LOGITS
     drives
    0.07
     pela
    0.07
     Colin
    0.06
    Snapshot
    0.06
    _Bl
    0.06
    ]').
    0.06
    _TRACE
    0.06
     ****************************************************************************
    0.06
    _mime
    0.06
     Герм
    0.06
    Act Density 0.032%

    No Known Activations