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

    Neuronpedia

    INDEX
    Explanations

    Control

    np_max-act · gemini-2.0-flash

    This neuron detects XAML/HTML-style closing tags (tokens starting with “</”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     advertisements
    -0.06
     CharSequence
    -0.06
     Infant
    -0.06
     이루
    -0.06
     степ
    -0.06
    .myapplication
    -0.06
     alignSelf
    -0.06
    ัวเอง
    -0.06
    افي
    -0.06
     fromDate
    -0.06
    POSITIVE LOGITS
     línea
    0.08
    tero
    0.07
    ποτε
    0.07
    actus
    0.06
     jours
    0.06
    τικο
    0.06
     abort
    0.06
     euth
    0.06
    امه
    0.06
    dbh
    0.06
    Act Density 0.002%

    No Known Activations