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

    Neuronpedia

    INDEX
    Explanations

    taking over or up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rolex
    0.98
     OI
    0.96
     PartialEq
    0.93
    ই
    0.92
    M
    0.91
    ↵
    0.90
    tze
    0.90
    锭
    0.90
    ia
    0.88
    t
    0.88
    POSITIVE LOGITS
    ü
    1.06
    ுகள்
    0.95
    ுகளை
    0.95
    ُ
    0.86
    ا
    0.85
    𝐮
    0.85
    훙
    0.85
    ా
    0.85
    𝐴
    0.85
    iciência
    0.84
    Act Density 0.073%

    No Known Activations