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

    Neuronpedia

    INDEX
    Explanations

    Research papers about circulation

    np_max-act · gemini-2.0-flash

    This neuron fires on the word “circulating” (or its fragment “Circ…”), especially when it appears as the heading/title at the start of a section.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nobel
    -0.08
    "No
    -0.08
     Noah
    -0.08
     protein
    -0.07
     websites
    -0.07
    “No
    -0.07
     Joel
    -0.07
     tai
    -0.07
    Adam
    -0.07
     bean
    -0.07
    POSITIVE LOGITS
     circ
    0.12
     circulation
    0.10
     Circ
    0.09
    irc
    0.09
     circulating
    0.08
    circ
    0.08
     Circus
    0.08
    vise
    0.08
    umont
    0.08
    ções
    0.08
    Act Density 0.011%

    No Known Activations