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

    Neuronpedia

    INDEX
    Explanations

    XML and HTML attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ကြည့်
    0.42
    Titles
    0.39
    Ending
    0.37
    玑
    0.36
    าก
    0.36
    colnames
    0.36
     caractères
    0.36
    titles
    0.36
     درب
    0.35
     اسماء
    0.35
    POSITIVE LOGITS
     />
    0.52
    =""/>
    0.41
    name
    0.40
    雖
    0.38
    とはいえ
    0.37
     δή
    0.37
     value
    0.37
    }^{*}(\
    0.37
    factory
    0.36
     unless
    0.36
    Act Density 0.002%

    No Known Activations