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

    Neuronpedia

    INDEX
    Explanations

    article followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存在的
    1.00
     overstated
    0.85
     सौंप
    0.85
     btw
    0.79
     upbringing
    0.79
    遇到的
    0.78
     موجود
    0.76
     myös
    0.75
     eftersom
    0.75
    。",
    0.75
    POSITIVE LOGITS
     doors
    1.15
     wheels
    1.07
    doors
    0.98
     hostilities
    0.97
     lights
    0.92
     gates
    0.92
     curtains
    0.91
    wheels
    0.91
     skies
    0.89
     seeds
    0.86
    Act Density 0.273%

    No Known Activations