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

    Neuronpedia

    INDEX
    Explanations

    governor and governance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    து
    1.93
     juríd
    1.77
     geographies
    1.70
    ิน
    1.56
     bottled
    1.51
     equated
    1.48
    ні
    1.47
    вая
    1.47
    적인
    1.47
     restrooms
    1.45
    POSITIVE LOGITS
    および
    2.23
    ссию
    2.05
    ς
    2.03
    sion
    1.99
    제목
    1.99
    iš
    1.96
    ﻧ
    1.96
    ため
    1.89
    うち
    1.89
    ्यारह
    1.88
    Act Density 0.007%

    No Known Activations