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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron reliably fires on very common English function words (e.g. “the,” “an,” “in,” “plus”), effectively detecting articles and simple prepositions in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     combo
    -0.07
    	ob
    -0.07
     Proposal
    -0.06
    _Header
    -0.06
     challeng
    -0.06
     springfox
    -0.06
     fullname
    -0.06
     Shemale
    -0.06
     InternalEnumerator
    -0.06
    thead
    -0.06
    POSITIVE LOGITS
     ⇒
    0.07
    령
    0.07
     هنگام
    0.06
     작업
    0.06
    .MM
    0.06
    ぎ
    0.06
     ліс
    0.06
    له
    0.06
    �
    0.06
     nejlepší
    0.06
    Act Density 0.040%

    No Known Activations