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

    Neuronpedia

    INDEX
    Explanations

    lawyers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONTROL
    -0.07
     Lilly
    -0.06
     cycl
    -0.06
    rebbe
    -0.06
    UNITY
    -0.06
     Özellikle
    -0.06
    IVED
    -0.06
    十分
    -0.06
    RIPT
    -0.06
    ials
    -0.06
    POSITIVE LOGITS
     lawyer
    0.08
     Lawyers
    0.07
     Lawyer
    0.07
    方面
    0.07
    earchBar
    0.07
     nomination
    0.07
     {}
↵
↵
    0.07
     lawyers
    0.06
     Edge
    0.06
     workers
    0.06
    Act Density 0.012%

    No Known Activations