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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash

    The neuron detects Reuters byline/photo‐credit strings, i.e. the “REUTERS/ReporterName” attribution lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pricing
    -0.07
     pricing
    -0.06
     Nunes
    -0.06
    宜
    -0.06
    (and
    -0.06
    amientos
    -0.06
    -appointed
    -0.06
     Resistance
    -0.06
    ological
    -0.06
     fragmentation
    -0.06
    POSITIVE LOGITS
     melan
    0.06
     outras
    0.06
    fieldName
    0.06
    寸
    0.06
    -Smith
    0.06
    .Model
    0.06
    Lou
    0.06
    前
    0.06
    된다
    0.06
    ウト
    0.06
    Act Density 0.009%

    No Known Activations