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

    Neuronpedia

    INDEX
    Explanations

    means the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     his
    0.51
     i
    0.46
     aurora
    0.45
     retina
    0.44
     සහ
    0.42
     iris
    0.42
    ㅕ
    0.42
     Gazprom
    0.42
    andam
    0.42
    맞
    0.42
    POSITIVE LOGITS
     Beginners
    0.46
     wichtigsten
    0.46
     Temperaturen
    0.45
     Variables
    0.44
     kamen
    0.43
     zeuden
    0.43
    混凝
    0.42
     pequeños
    0.41
     Factors
    0.41
     unang
    0.41
    Act Density 0.002%

    No Known Activations