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

    Neuronpedia

    INDEX
    Explanations

    .set or .GetValue

    np_max-act · gemini-2.0-flash

    The neuron fires on Java reflection calls (e.g. getDeclaredField/Method, setAccessible, getLong, invoke, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     perv
    -0.06
     Bauer
    -0.06
     CIA
    -0.06
    协议
    -0.06
    elled
    -0.06
    foil
    -0.06
     관심
    -0.06
     městě
    -0.06
     incontro
    -0.06
     같이
    -0.06
    POSITIVE LOGITS
    ایع
    0.07
     almacen
    0.06
    _flow
    0.06
    $s
    0.06
    55
    0.06
     nabízí
    0.06
     Insights
    0.06
     immortal
    0.06
    'image
    0.06
    -bre
    0.06
    Act Density 0.003%

    No Known Activations