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

    Neuronpedia

    INDEX
    Explanations

    Chinese; infrastructure and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nvidia
    -0.08
    lado
    -0.08
     Grammy
    -0.08
     keto
    -0.08
     decidedly
    -0.07
    ੱਲ
    -0.07
    ਲ
    -0.07
    ikler
    -0.07
    istle
    -0.07
    -0.07
    POSITIVE LOGITS
    威
    0.10
     威
    0.09
    省
    0.09
     �
    0.09
    岗位
    0.08
     helpless
    0.08
    提升
    0.08
    公安
    0.08
     entrusted
    0.08
    尊
    0.08
    Act Density 0.315%
    No Known Activations