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

    Neuronpedia

    INDEX
    Explanations

    track

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of progress tracking—particularly phrases like “on track” or similar expressions indicating status toward goals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iquid
    -0.07
    ighbour
    -0.06
    Fat
    -0.06
    SocketAddress
    -0.06
     Specialists
    -0.06
    (namespace
    -0.06
     esto
    -0.06
     Něk
    -0.06
     côt
    -0.06
     street
    -0.06
    POSITIVE LOGITS
    aysia
    0.07
    itta
    0.07
     :,
    0.07
    일반
    0.06
    >")
    0.06
    109
    0.06
    .prev
    0.06
    ância
    0.06
     آنلاین
    0.06
    pheric
    0.06
    Act Density 0.008%

    No Known Activations