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

    Neuronpedia

    INDEX
    Explanations

    if not divisible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ቒ
    0.44
    㢦
    0.40
    只限平日
    0.39
    كلة
    0.39
    ্ত্র
    0.39
    Mountain
    0.38
    大赛
    0.38
    ግሎ
    0.38
    Mountains
    0.38
     kand
    0.37
    POSITIVE LOGITS
     захи
    0.38
    ედა
    0.37
     yksi
    0.37
     Multi
    0.36
     Facilit
    0.36
     Alpha
    0.35
     termite
    0.35
     Verteid
    0.35
     Jeopardy
    0.34
     Bag
    0.34
    Act Density 0.000%

    No Known Activations