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

    Neuronpedia

    INDEX
    Explanations

    uron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SCM
    -0.08
    座谈
    -0.08
    黻
    -0.07
    Ordinal
    -0.07
    ℱ
    -0.07
     Chu
    -0.07
     Instrument
    -0.06
    live
    -0.06
    _allocation
    -0.06
    larından
    -0.06
    POSITIVE LOGITS
    质量问题
    0.07
     sonrası
    0.07
     prolifer
    0.06
    疠
    0.06
    之日起
    0.06
    🕶
    0.06
     Cover
    0.06
    公安局
    0.06
    ackages
    0.06
    orrent
    0.06
    Act Density 0.001%

    No Known Activations