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

    Neuronpedia

    INDEX
    Explanations

    long straights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inar
    1.23
    NSInteger
    1.22
    resx
    1.18
     nullable
    1.15
     confused
    1.15
     embroidery
    1.14
    PlatformToolset
    1.13
     ма
    1.13
     Embroidery
    1.12
    NavigationBar
    1.11
    POSITIVE LOGITS
    ات
    1.52
    ের
    1.13
    s
    1.05
     bomb
    1.04
     ego
    1.04
    E
    1.04
    Egy
    1.02
    फोन
    1.00
    <h2>
    1.00
    ы
    1.00
    Act Density 0.034%

    No Known Activations