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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to sentence-initial or clause-opening discourse markers and explanatory connectors (e.g. “It’s,” “While,” “This,” “how”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    都会
    -0.06
    According
    -0.06
    Ф
    -0.06
     thỏa
    -0.06
     spills
    -0.06
     طبی
    -0.06
    Fabric
    -0.06
    iding
    -0.06
     Mediterr
    -0.06
     примерно
    -0.06
    POSITIVE LOGITS
     crawl
    0.07
    akin
    0.07
     tu
    0.06
    StringEncoding
    0.06
     characteristic
    0.06
     aktif
    0.06
    /group
    0.06
    _gc
    0.06
     contamination
    0.06
     filenames
    0.06
    Act Density 0.102%

    No Known Activations