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

    Neuronpedia

    INDEX
    Explanations

    biological processes

    np_max-act · gemini-2.0-flash

    This neuron detects nominalized process terms—nouns like “sensitivity,” “inhibition,” “modulation,” “stimulation,” “control,” or “digestion” that introduce biochemical or experimental procedure phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prostřed
    -0.07
    鋼
    -0.06
    stories
    -0.06
    imators
    -0.06
     hakk
    -0.06
    ![↵
    -0.06
    anno
    -0.06
    dığını
    -0.06
    virtual
    -0.06
    ิดข
    -0.06
    POSITIVE LOGITS
     Anders
    0.06
     pierws
    0.06
    Inline
    0.06
     бать
    0.06
    _RADIO
    0.06
    _DIALOG
    0.06
     Πολ
    0.06
    hasClass
    0.06
     说
    0.06
    Κ
    0.06
    Act Density 0.065%

    No Known Activations