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

    Neuronpedia

    INDEX
    Explanations

    code wrapping/delegation

    np_max-act · gemini-2.0-flash

    The neuron fires on code that’s delegating calls—i.e. references to a “delegate” field or invocations of methods on a delegate object.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pos
    -0.06
     negligible
    -0.06
    lerimiz
    -0.06
     OPTIONAL
    -0.06
    erap
    -0.06
    在线阅读
    -0.06
    uí
    -0.06
    yaw
    -0.06
    agus
    -0.06
    ’all
    -0.06
    POSITIVE LOGITS
     �
    0.07
     Sym
    0.06
    Reason
    0.06
    esy
    0.06
     horses
    0.06
    好的
    0.06
     خام
    0.06
     Broncos
    0.06
     плеч
    0.06
    Projected
    0.06
    Act Density 0.010%

    No Known Activations