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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    This neuron activates on the particle “up,” particularly when it appears in phrasal verbs like “pop up,” “show up,” or “bump up.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ('${
    -0.07
    _shutdown
    -0.07
    goo
    -0.06
     ensures
    -0.06
    -acre
    -0.06
     ensure
    -0.06
     desi
    -0.06
     Okay
    -0.06
     حکومت
    -0.06
    -manager
    -0.06
    POSITIVE LOGITS
     appear
    0.09
     appeared
    0.09
     appears
    0.08
     appearing
    0.08
     emerged
    0.07
     UPC
    0.07
     올
    0.07
     ''),↵
    0.07
    ึ้
    0.07
     얼굴
    0.07
    Act Density 0.035%

    No Known Activations