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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     department
    -1.02
    department
    -0.90
     Department
    -0.86
    Department
    -0.84
     DEPARTMENT
    -0.83
     dept
    -0.75
    DEPARTMENT
    -0.70
    Dept
    -0.69
     Dept
    -0.67
     département
    -0.65
    POSITIVE LOGITS
     Paglinawan
    0.53
    <bos>
    0.50
    })()
    0.50
    SharedDtor
    0.49
     gespannt
    0.49
    ]")]
    0.49
     Charlemagne
    0.49
    WindowConstants
    0.48
    BuildContext
    0.47
    al
    0.47
    Act Density 0.031%

    No Known Activations