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

    Neuronpedia

    INDEX
    Explanations

    player, class, color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LOTRE
    0.49
     सुझाव
    0.47
     ব্যবসার
    0.46
    🎷
    0.44
    ेच्छा
    0.44
    𝙙
    0.44
    норийска
    0.43
     titleImageUrl
    0.43
    ⧐
    0.43
    ธุรก
    0.43
    POSITIVE LOGITS
    ’
    0.43
    訓練
    0.41
     class
    0.41
    ↵
    0.40
     player
    0.39
     classes
    0.39
     genotypes
    0.38
     color
    0.38
     hordes
    0.38
     rival
    0.38
    Act Density 0.052%

    No Known Activations