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

    Neuronpedia

    INDEX
    Explanations

    verbs related to answering questions

    np_max-act · gemini-2.0-flash

    incomplete comparative statements about quantities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects expressions of insufficient information or impossibility, e.g. “not possible to determine.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ocolate
    -0.08
    _sl
    -0.07
     lý
    -0.07
     віднос
    -0.07
    emos
    -0.07
     Ct
    -0.07
     assertion
    -0.06
     içeren
    -0.06
    unicorn
    -0.06
    職
    -0.06
    POSITIVE LOGITS
     {$
    0.07
    moid
    0.06
    일반
    0.06
    _TRI
    0.06
     Vitamin
    0.06
    лу
    0.06
    levator
    0.06
    hare
    0.06
     imkan
    0.06
    lenme
    0.06
    Act Density 0.026%

    No Known Activations