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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron appears effectively inactive and does not detect any particular tokens or patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _CHARS
    -0.07
    462
    -0.06
    480
    -0.06
    376
    -0.06
     товарів
    -0.06
    ้ท
    -0.06
    Ad
    -0.06
    486
    -0.06
     электрон
    -0.06
     detox
    -0.06
    POSITIVE LOGITS
     sql
    0.07
     butcher
    0.06
     Parallel
    0.06
     oracle
    0.06
     wik
    0.06
     recap
    0.06
     내
    0.06
     Sure
    0.06
    (integer
    0.06
    (existing
    0.06
    Act Density 0.038%

    No Known Activations