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

    Neuronpedia

    INDEX
    Explanations

    Galaxy

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on the word “Galaxy,” identifying occurrences of that specific term.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    18
    -0.08
    8
    -0.07
     스트
    -0.07
    19
    -0.07
     noise
    -0.07
    15
    -0.07
     Moore
    -0.07
     Wimbledon
    -0.07
     NoSuchElementException
    -0.07
    .ActionListener
    -0.07
    POSITIVE LOGITS
     gal
    0.13
     galaxy
    0.11
     Galaxy
    0.11
     galaxies
    0.10
     Gal
    0.09
    izon
    0.09
    Gal
    0.08
     gallon
    0.08
     Galactic
    0.08
    agal
    0.08
    Act Density 0.010%

    No Known Activations