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

    Neuronpedia

    INDEX
    Explanations

    Recording

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect disclosures that the call may be recorded or monitored.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hover
    -0.06
    .Log
    -0.06
     مبار
    -0.06
     mascot
    -0.06
     nap
    -0.06
    폐
    -0.06
    اج
    -0.06
     مهر
    -0.06
    计划
    -0.06
    incible
    -0.06
    POSITIVE LOGITS
    .toLocale
    0.07
     California
    0.07
    -analysis
    0.06
     misguided
    0.06
    (price
    0.06
    .AC
    0.06
    -initialized
    0.06
     находится
    0.06
    국의
    0.06
     Configuration
    0.06
    Act Density 0.003%

    No Known Activations