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

    Neuronpedia

    INDEX
    Explanations

    coding questions

    np_max-act · gemini-2.0-flash

    This neuron activates on the key specification words (like “based,” “on,” “criterion,” and surrounding articles) that describe the selection criterion in a spreadsheet/formula question.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     iron
    -0.07
    select
    -0.07
    หว
    -0.07
     None
    -0.07
    沉
    -0.07
     ions
    -0.07
     silent
    -0.06
    trying
    -0.06
    かけ
    -0.06
     knock
    -0.06
    POSITIVE LOGITS
    itecture
    0.06
    opol
    0.06
     smartphones
    0.06
    icopter
    0.06
    _android
    0.06
     waters
    0.06
     марш
    0.06
     İç
    0.05
    روش
    0.05
     returnUrl
    0.05
    Act Density 0.103%

    No Known Activations