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

    Neuronpedia

    INDEX
    Explanations

    function definition `def`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ോഷ്യ
    0.46
     Dors
    0.46
     et
    0.44
     Polymers
    0.44
     perfusion
    0.43
     hvor
    0.42
     Pharmaceuticals
    0.42
    GFR
    0.42
    陏
    0.42
    जफ्
    0.41
    POSITIVE LOGITS
    def
    0.71
    Def
    0.54
     def
    0.52
    defn
    0.52
     Def
    0.51
     定义
    0.44
    quela
    0.43
     бренда
    0.42
    defender
    0.41
     defensively
    0.41
    Act Density 0.013%

    No Known Activations