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

    Neuronpedia

    INDEX
    Explanations

    Bit error rate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scent
    -0.10
     rebound
    -0.09
    authority
    -0.09
     scents
    -0.09
     immobili
    -0.09
     Hemp
    -0.09
     inmobili
    -0.09
     Runner
    -0.09
    yin
    -0.09
     kindness
    -0.08
    POSITIVE LOGITS
     throughput
    0.11
    性能
    0.11
     degrading
    0.10
     BER
    0.10
     degradation
    0.10
     degrade
    0.10
     retrans
    0.10
     outage
    0.10
     waveform
    0.10
    _crc
    0.10
    Act Density 0.006%

    No Known Activations