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

    Neuronpedia

    INDEX
    Explanations

    additional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adequate
    -0.98
    ्यालय
    -0.96
    Among
    -0.94
     sebagainya
    -0.93
     adecuados
    -0.93
     manguera
    -0.91
    ليه
    -0.91
    اقل
    -0.91
     preescolar
    -0.88
    之一
    -0.88
    POSITIVE LOGITS
     beyond
    2.03
    beyond
    1.88
     than
    1.83
     added
    1.66
     additional
    1.52
     추가
    1.48
     zusätzlichen
    1.40
     zusätzliche
    1.39
     além
    1.38
     oltre
    1.35
    Act Density 0.066%

    No Known Activations