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

    Neuronpedia

    INDEX
    Explanations

    win rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gifts
    0.76
     gifts
    0.75
    èques
    0.74
     regalo
    0.71
    apaccay
    0.71
     Gifts
    0.70
    𝚃
    0.70
     coverings
    0.70
    𝙄
    0.69
     chemins
    0.68
    POSITIVE LOGITS
     sai
    0.85
    Droid
    0.69
    bal
    0.67
    스트
    0.66
     프린
    0.66
     kerja
    0.66
    مارسة
    0.65
    BAL
    0.64
    בודה
    0.64
     ஏற்பட
    0.64
    Act Density 0.000%

    No Known Activations