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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of GNU license header keywords (e.g. “GNU General Public License”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sleeper
    -0.07
     Gale
    -0.06
     shadow
    -0.06
     nors
    -0.06
    freeze
    -0.06
     flock
    -0.06
    rand
    -0.06
     shame
    -0.06
     Bed
    -0.06
     JW
    -0.06
    POSITIVE LOGITS
    0.10
     nghiên
    0.08
    0.07
    _VERIFY
    0.07
    0.07
    ListItem
    0.07
     추가
    0.07
    0.07
    (turn
    0.07
    ителей
    0.06
    Act Density 0.001%

    No Known Activations