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

    Neuronpedia

    INDEX
    Explanations

    SwiftUI"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✠
    1.03
     alternating
    0.94
    दंड
    0.86
    '>";
    0.85
     imbalances
    0.85
    ziest
    0.85
    只要
    0.84
     landslides
    0.84
    ➖➖
    0.84
     heaped
    0.83
    POSITIVE LOGITS
    т
    1.14
    ITIONAL
    0.89
    办法
    0.86
    น
    0.85
    ype
    0.81
    Bris
    0.80
    tig
    0.79
    ゙
    0.79
    ก
    0.78
    마
    0.78
    Act Density 0.003%

    No Known Activations