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

    Neuronpedia

    INDEX
    Explanations

    English vowel sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     [
    0.92
      
    0.78
    <0xC2>
    0.74
     (
    0.74
     ­
    0.72
     (?)
    0.63
    rec
    0.63
     ["
    0.61
     [$
    0.60
     []
    0.60
    POSITIVE LOGITS
     파일
    0.94
     EnglishChoose
    0.93
     gebruikt
    0.91
     download
    0.89
    uploaded
    0.88
    사이트
    0.88
     ファイル
    0.87
    システムの
    0.87
    几年
    0.86
     घोड़ा
    0.86
    Act Density 0.006%

    No Known Activations