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

    Neuronpedia

    INDEX
    Explanations

    Formal language

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to short grammatical connector words (function words) in running text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unpl
    -0.07
     militant
    -0.07
     Fuk
    -0.06
    ánchez
    -0.06
     laboratories
    -0.06
     iz
    -0.06
    que
    -0.06
     Ibn
    -0.06
    viz
    -0.06
     instruction
    -0.06
    POSITIVE LOGITS
    ються
    0.08
     této
    0.07
     Dare
    0.06
     موبایل
    0.06
     acciones
    0.06
    ')}>↵
    0.06
     ONLY
    0.06
    。他
    0.06
    								↵
    0.06
     Trash
    0.06
    Act Density 0.136%

    No Known Activations