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

    Neuronpedia

    INDEX
    Explanations

    School

    np_max-act · gemini-2.0-flash

    This neuron responds to narrative‐opening and fantasy‐setting phrases—especially classic story introductions like “Once upon a time…” and terms that set up a magical school tale.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Comm
    -0.06
     gland
    -0.06
    answers
    -0.06
     cott
    -0.06
    _integer
    -0.06
    _XDECREF
    -0.06
    infile
    -0.06
    рения
    -0.06
     pastry
    -0.06
    інки
    -0.06
    POSITIVE LOGITS
    (Vec
    0.07
    	make
    0.07
     Omni
    0.06
    ileaks
    0.06
    roperties
    0.06
     priceless
    0.06
    Lastly
    0.06
    ={}
    0.06
    _:
    0.06
    rač
    0.06
    Act Density 0.011%

    No Known Activations