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

    Neuronpedia

    INDEX
    Explanations

    forming a government?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geograf
    0.49
     khá
    0.48
     ตาม
    0.46
     bệnh
    0.43
     `'\\
    0.43
    𝐟
    0.42
    lıkla
    0.42
    <unused83>
    0.42
     bohat
    0.42
     ді
    0.42
    POSITIVE LOGITS
    ’
    0.72
    (
    0.46
    0
    0.42
    Government
    0.41
    government
    0.40
    Trying
    0.39
    H
    0.39
    O
    0.39
    ’:
    0.37
    is
    0.37
    Act Density 1.603%

    No Known Activations