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

    Neuronpedia

    INDEX
    Explanations

    focus and attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ствий
    0.69
    ല്ലാതെ
    0.69
    ස්ථ
    0.62
    नाची
    0.58
    শ্বর
    0.56
     übrigens
    0.54
    uminescence
    0.53
    льня
    0.53
    வக
    0.53
    рят
    0.53
    POSITIVE LOGITS
     focus
    5.83
    focus
    5.38
    Focus
    5.32
     Focus
    5.32
     focusing
    5.14
     focuses
    5.03
     focused
    4.91
     focussing
    4.80
     Focusing
    4.78
     fokus
    4.76
    Act Density 2.867%

    No Known Activations