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

    Neuronpedia

    INDEX
    Explanations

    list items or enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    composite
    0.38
    union
    0.38
     composite
    0.38
    തിൽ
    0.38
    תה
    0.37
    Composite
    0.37
    ندی
    0.36
     composites
    0.36
    isComposite
    0.35
     appContext
    0.34
    POSITIVE LOGITS
     APPE
    0.40
    *%
    0.40
    ﹁
    0.40
     다섯
    0.40
    ຳ
    0.39
    ﮨ
    0.39
     consultancy
    0.39
    يكا
    0.39
    %。
    0.38
     allez
    0.38
    Act Density 0.000%

    No Known Activations