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

    Neuronpedia

    INDEX
    Explanations

    Art, media, and creative expression

    np_max-act · gemini-2.0-flash

    The neuron lights up on words that appear as paired items in “X and Y” or “X or Y” constructions—i.e. tokens in two-element coordination lists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    content related to animal adoption and rescue.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    /msg
    -0.07
    "description
    -0.07
    HEY
    -0.06
    stud
    -0.06
     every
    -0.06
    dq
    -0.06
     Drill
    -0.06
     Rohingya
    -0.06
     CIA
    -0.06
     Gün
    -0.06
    POSITIVE LOGITS
     �
    0.07
    іг
    0.06
     cancell
    0.06
    ующ
    0.06
     NAFTA
    0.06
     DAL
    0.06
     eventual
    0.06
    への
    0.06
     bootloader
    0.06
     гиб
    0.06
    Act Density 0.110%

    No Known Activations