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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron fires on attention-grabbing, promotional lead-in phrases (often in all-caps or with exclamation marks) used to headline or advertise real-estate listings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Cursor
    -0.07
     td
    -0.06
     Serious
    -0.06
    .Cursors
    -0.06
    اسه
    -0.06
    angent
    -0.06
     Princeton
    -0.06
    ds
    -0.06
    linewidth
    -0.06
    	connect
    -0.06
    POSITIVE LOGITS
     всі
    0.07
    bě
    0.06
    :'',
    0.06
     Sega
    0.06
    Лю
    0.06
     grosse
    0.06
    .setRotation
    0.06
    メラ
    0.06
    _addr
    0.06
    iflower
    0.06
    Act Density 0.020%

    No Known Activations