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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash

    The neuron fires on first‐person “I” requests or statements of desire/need (e.g. “I want,” “I would settle for,” “I need”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     receptive
    -0.08
    라
    -0.07
    _shipping
    -0.07
     active
    -0.06
     già
    -0.06
    ैठ
    -0.06
    ávat
    -0.06
    玛
    -0.06
    planet
    -0.06
     hảo
    -0.06
    POSITIVE LOGITS
    щины
    0.07
    (NS
    0.07
     �
    0.06
     Ř
    0.06
     Lis
    0.06
    аблиц
    0.06
     �
    0.06
     tableLayoutPanel
    0.06
     Я
    0.06
    wert
    0.06
    Act Density 0.164%

    No Known Activations