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

    Neuronpedia

    INDEX
    Explanations

    license compact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क्षा
    0.73
    ниці
    0.71
     ஏ
    0.68
     منظر
    0.67
     Environmental
    0.66
     Morrissey
    0.66
     Commission
    0.65
     লঙ্ঘন
    0.65
    romo
    0.64
     Sunflower
    0.64
    POSITIVE LOGITS
    θν
    0.93
    ים
    0.83
    ের
    0.76
    s
    0.75
    ς
    0.74
    बर्ग
    0.72
    സ്ട
    0.71
    écl
    0.70
     europeos
    0.69
    ഷ്ട്ര
    0.67
    Act Density 0.001%

    No Known Activations