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

    Neuronpedia

    INDEX
    Explanations

    describing limitations or lack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಪ್ರಕರಣ
    0.43
    താണ
    0.40
    રમાં
    0.39
    南極
    0.38
    rH
    0.38
    ahon
    0.37
     सहार
    0.37
    wapV
    0.36
     Lp
    0.36
    히려
    0.36
    POSITIVE LOGITS
     lacks
    0.67
     only
    0.60
    无法
    0.59
     lacking
    0.58
    缺乏
    0.57
     cannot
    0.56
     нельзя
    0.55
     lack
    0.53
     unable
    0.52
     desperately
    0.52
    Act Density 0.169%

    No Known Activations