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

    Neuronpedia

    INDEX
    Explanations

    government actions and policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.85
    ка
    0.79
    larda
    0.74
     português
    0.71
     humana
    0.70
    كيف
    0.69
    ように
    0.68
     ді
    0.68
     predom
    0.68
     distint
    0.67
    POSITIVE LOGITS
    is
    1.17
    ad
    0.97
    H
    0.90
    ine
    0.88
    government
    0.82
    id
    0.82
    Government
    0.80
    V
    0.79
    S
    0.77
    (
    0.77
    Act Density 0.010%

    No Known Activations