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

    Neuronpedia

    INDEX
    Explanations

    C# code snippets and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EventArgs
    0.43
    Xamarin
    0.41
     foreach
    0.41
     nameof
    0.41
    foreach
    0.41
     ఆయన
    0.40
     Story
    0.38
     Що
    0.38
    项
    0.38
    toolStrip
    0.38
    POSITIVE LOGITS
     dh
    0.46
    effective
    0.46
     bottled
    0.45
    static
    0.44
    dh
    0.43
    savings
    0.43
    nov
    0.43
    oi
    0.43
    internal
    0.42
     internal
    0.42
    Act Density 0.002%

    No Known Activations