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

    Neuronpedia

    INDEX
    Explanations

    statements

    np_max-act · gemini-2.0-flash

    This neuron responds to the core definition sentence that says a summary is factually consistent if “all statements in the summary are entailed by the document.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    وره
    -0.08
    okers
    -0.07
    ousedown
    -0.06
    Creators
    -0.06
    Danger
    -0.06
    角
    -0.06
    ùy
    -0.06
    اءات
    -0.06
    讯
    -0.06
    Matches
    -0.06
    POSITIVE LOGITS
    .Txt
    0.07
     contempt
    0.07
     depicting
    0.06
    ="-
    0.06
     vat
    0.06
     pledged
    0.06
     komen
    0.06
     altern
    0.06
    _LOWER
    0.06
    .api
    0.06
    Act Density 0.001%

    No Known Activations