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

    Neuronpedia

    INDEX
    Explanations

    behind

    np_max-act · gemini-2.0-flash

    The neuron detects language describing concrete, physical or spatial qualities—words and phrases that evoke something tangible or three‐dimensional.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     toddler
    -0.07
     optical
    -0.06
     Negro
    -0.06
    _bm
    -0.06
    .edu
    -0.06
     Optical
    -0.06
    ullivan
    -0.06
    ScrollBar
    -0.06
    воля
    -0.06
     société
    -0.06
    POSITIVE LOGITS
     proclaim
    0.06
    وذ
    0.06
     assum
    0.06
    опрос
    0.06
     punch
    0.06
    Cancel
    0.06
     jars
    0.06
     GetById
    0.06
    RESOURCE
    0.06
     rin
    0.06
    Act Density 0.241%

    No Known Activations