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

    Neuronpedia

    INDEX
    Explanations

    classic riddle or trick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.53
     of
    0.52
    "
    0.46
     workforce
    0.44
     habit
    0.43
     apparten
    0.42
     recreational
    0.42
     ())
    0.42
     racetrack
    0.42
     rounds
    0.42
    POSITIVE LOGITS
     صہیونیت
    0.51
    popupIsOpen
    0.48
    ഴിഞ്ഞ
    0.48
     kapital
    0.47
    ɥ
    0.47
    ildiği
    0.46
    穸
    0.46
    साल
    0.45
    isVideo
    0.45
    कृति
    0.44
    Act Density 0.004%

    No Known Activations