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

    Neuronpedia

    INDEX
    Explanations

    detecting independence after articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    რავ
    0.67
     رحمت
    0.66
    uram
    0.66
     ক্ষতির
    0.66
    ުރ
    0.63
    ཥ
    0.63
    惋
    0.61
    遗憾
    0.61
     Usual
    0.60
    _{+
    0.60
    POSITIVE LOGITS
     independent
    4.33
     independence
    4.04
    independent
    3.93
    Independent
    3.90
    独立
    3.82
     independ
    3.78
     Independent
    3.76
     independently
    3.73
     independiente
    3.73
     independientes
    3.70
    Act Density 0.311%

    No Known Activations