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

    Neuronpedia

    INDEX
    Explanations

    mat

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of specific product names or categories (e.g. appliances, consumer‐goods items).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .drag
    -0.08
     tilted
    -0.07
    imating
    -0.06
    อนด
    -0.06
    -pre
    -0.06
     اسپ
    -0.06
    progressbar
    -0.06
    iveness
    -0.06
    takes
    -0.06
    носят
    -0.06
    POSITIVE LOGITS
    Reports
    0.07
    0.07
     �
    0.07
     (--
    0.06
    	super
    0.06
     abre
    0.06
     accordion
    0.06
     elev
    0.06
    PDOException
    0.06
    medical
    0.06
    Act Density 0.055%

    No Known Activations