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

    Neuronpedia

    INDEX
    Explanations

    garnishes or decorations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    1.95
    ن
    1.82
     for
    1.70
    ल
    1.52
    ش
    1.48
     as
    1.38
    न
    1.36
    ল
    1.34
    ק
    1.31
    ন
    1.27
    POSITIVE LOGITS
    ۹
    1.42
    는
    1.39
    ید
    1.29
    .
    1.27
    ۵
    1.20
    ುತ್ತೇನೆ
    1.15
    টি
    1.11
    見える
    1.11
    は
    1.11
    ۔
    1.05
    Act Density 0.000%

    No Known Activations