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

    Neuronpedia

    INDEX
    Explanations

    javascript function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.50
    i
    0.48
     cierto
    0.47
    ﯽ
    0.47
     censoring
    0.46
     reels
    0.46
    cdot
    0.45
     গুরুত্ব
    0.44
    0
    0.44
     此
    0.43
    POSITIVE LOGITS
    ிருக்கிற
    0.54
    a
    0.50
    к
    0.50
    تو
    0.50
    ()?
    0.50
     બનાવવા
    0.49
     도
    0.49
     धाराओं
    0.49
    ?(
    0.48
    क
    0.48
    Act Density 0.006%

    No Known Activations