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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of specific facility or building counts (e.g. “three laboratories,” “computer lab,” “dormitories”), detecting numeric specifications of physical infrastructure.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bayer
    -0.07
    ỉnh
    -0.06
    ihu
    -0.06
    端
    -0.06
    /gtest
    -0.06
     GEN
    -0.06
    58
    -0.06
    _Font
    -0.06
    ANE
    -0.06
    Metrics
    -0.06
    POSITIVE LOGITS
     Monster
    0.07
     Microwave
    0.07
    (serv
    0.07
    *S
    0.06
     Hobby
    0.06
    ními
    0.06
    ##
    0.06
    !'
    0.06
     celebrates
    0.06
    451
    0.06
    Act Density 0.031%

    No Known Activations