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 responds to the typical introductory or transition words and phrases that begin sentences in patent-style technical descriptions (e.g. “To,” “The,” “Accordingly,” “It is,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ाहर
    -0.07
     reloading
    -0.07
     Aware
    -0.06
     Worship
    -0.06
    膜
    -0.06
     alır
    -0.06
    ADDE
    -0.06
     below
    -0.06
     Shiv
    -0.06
    _cre
    -0.06
    POSITIVE LOGITS
    (newValue
    0.06
     Wesley
    0.06
    クリ
    0.06
     сильно
    0.06
    ắc
    0.06
     pour
    0.06
     obsah
    0.06
    чив
    0.06
    ++];↵
    0.06
    asyonu
    0.06
    Act Density 0.014%

    No Known Activations