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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of table or grid rows (e.g. “row,” “rows,” or `<tr>`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jarvis
    -0.08
    _Output
    -0.07
    vice
    -0.06
     speech
    -0.06
     OCR
    -0.06
    products
    -0.06
     Stuff
    -0.06
     Tup
    -0.06
    Sir
    -0.06
     güzel
    -0.06
    POSITIVE LOGITS
     lurking
    0.09
    _effect
    0.07
    mon
    0.06
     colorWithRed
    0.06
     paints
    0.06
    ؤ
    0.06
    stocks
    0.06
    jpeg
    0.06
     مشکل
    0.06
     práci
    0.06
    Act Density 0.008%

    No Known Activations