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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculation and processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ανα
    0.46
    cfg
    0.46
     Ось
    0.44
     cleared
    0.44
    ணத்திற்கு
    0.44
     张
    0.43
    划分
    0.43
    柴
    0.43
    astaan
    0.42
    şı
    0.42
    POSITIVE LOGITS
    this
    0.58
     this
    0.53
     هذا
    0.52
     dette
    0.52
     этом
    0.46
     dieser
    0.45
     цього
    0.45
     calculating
    0.44
     calculer
    0.44
     calamities
    0.44
    Act Density 0.001%

    No Known Activations