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

    Neuronpedia

    INDEX
    Explanations

    C++ template syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dze
    0.44
    strMeal
    0.43
    öhn
    0.42
    ühlt
    0.41
     marshes
    0.41
    舐
    0.41
     शिकार
    0.40
    銛
    0.40
     mowing
    0.40
    送到
    0.40
    POSITIVE LOGITS
     template
    0.99
    template
    0.97
     Template
    0.80
    模板
    0.79
     templates
    0.79
    Template
    0.76
     Templates
    0.75
    テンプレート
    0.73
     typename
    0.71
     constexpr
    0.70
    Act Density 0.017%

    No Known Activations