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

    Neuronpedia

    INDEX
    Explanations

    state actions and governance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qí
    0.63
    其他
    0.61
     Tokugawa
    0.59
    𝐠
    0.59
    <unused1801>
    0.57
     Xie
    0.57
     оста
    0.56
    <unused1974>
    0.55
     օ
    0.55
     CtApp
    0.55
    POSITIVE LOGITS
    ’
    0.52
    \
    0.47
    ason
    0.45
    int
    0.42
    out
    0.42
    λ
    0.41
    res
    0.38
    I
    0.37
     degeneration
    0.37
    ן
    0.37
    Act Density 0.006%

    No Known Activations