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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on specialized, technical terminology characteristic of formal academic or scientific writing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Technology
    -0.07
    voje
    -0.06
    Guard
    -0.06
     packs
    -0.06
    .adv
    -0.06
     platforms
    -0.06
     piles
    -0.06
    _req
    -0.06
    frame
    -0.06
     Player
    -0.06
    POSITIVE LOGITS
     страх
    0.07
    ์ได
    0.07
    ITT
    0.07
     Dart
    0.07
    .toDouble
    0.06
     مض
    0.06
     dispon
    0.06
    】
    0.06
     مسجد
    0.06
    .Speed
    0.06
    Act Density 0.116%

    No Known Activations