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

    Neuronpedia

    INDEX
    Explanations

    air pollutants and contaminants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    1.10
    اک
    0.88
    सार
    0.86
    SM
    0.86
    \}.
    0.86
    。
    0.86
    र
    0.86
    "})
    0.83
    Mad
    0.81
     I
    0.81
    POSITIVE LOGITS
     contaminants
    0.80
    <0x91>
    0.80
     اثنين
    0.78
     materiál
    0.77
    se
    0.77
     be
    0.75
     thẻ
    0.75
     pollutants
    0.73
    <0x80>
    0.72
    д
    0.72
    Act Density 0.003%

    No Known Activations