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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash

    the neuron fires on utterances that express agreement/acknowledgement or apologies directed at the user (e.g., "You are right", "I apologize", "I understand").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    níku
    -0.07
     буде
    -0.07
    хов
    -0.07
    gr
    -0.06
    HEL
    -0.06
     Juli
    -0.06
    lahoma
    -0.06
     зави
    -0.06
    �
    -0.06
     coraz
    -0.06
    POSITIVE LOGITS
     marc
    0.08
     marque
    0.07
    Thank
    0.07
    および
    0.06
    }↵
    0.06
     mortal
    0.06
    ,↵
    0.06
     framerate
    0.06
    Struct
    0.06
    	Label
    0.06
    Act Density 0.065%

    No Known Activations