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

    Neuronpedia

    INDEX
    Explanations

    searchData

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by the identifier “searchData,” i.e. it detects the JavaScript variable name used to hold the documentation’s search‐index array.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     navCtrl
    -0.07
    ivalence
    -0.07
     outset
    -0.06
     trebuie
    -0.06
    hardware
    -0.06
    eated
    -0.06
     Williams
    -0.06
    isay
    -0.06
     mainstream
    -0.06
    ınma
    -0.06
    POSITIVE LOGITS
     searchData
    0.13
    .cloud
    0.07
     ("-
    0.07
    _sun
    0.06
     外部
    0.06
     meetup
    0.06
    (info
    0.06
    ––
    0.06
    .average
    0.06
     Developer
    0.06
    Act Density 0.000%

    No Known Activations