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

    Neuronpedia

    INDEX
    Explanations

    formal letters

    np_max-act · gemini-2.0-flash

    The neuron activates on the first‐person formal letter opening—especially the phrase “I am writing to.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     건강
    -0.06
     Checklist
    -0.06
     equival
    -0.06
     typu
    -0.06
     Buffered
    -0.06
     ・
    -0.06
    /G
    -0.06
    同步
    -0.06
     spared
    -0.06
    养
    -0.06
    POSITIVE LOGITS
    MAL
    0.07
     Hungarian
    0.06
    rases
    0.06
     congratulate
    0.06
     Plugin
    0.06
     PARK
    0.06
     weer
    0.06
     ray
    0.06
     enquanto
    0.06
    afe
    0.06
    Act Density 0.016%

    No Known Activations