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

    Neuronpedia

    INDEX
    Explanations

    Knowing or confirming something

    np_max-act · gemini-2.0-flash

    This neuron lights up on words and phrases expressing confidence or certainty (e.g. “know,” “sure,” “sure thing”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Improvement
    -0.08
    evice
    -0.08
     WF
    -0.07
    =center
    -0.07
    _skills
    -0.07
    _port
    -0.06
     key
    -0.06
    _pass
    -0.06
     improvement
    -0.06
     оч
    -0.06
    POSITIVE LOGITS
     mnoho
    0.07
     واح
    0.07
    ��
    0.06
     아�
    0.06
     фай
    0.06
    ++;
↵
    0.06
    .onView
    0.06
     Worldwide
    0.06
     деся
    0.06
    کا
    0.06
    Act Density 0.051%

    No Known Activations