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

    Neuronpedia

    INDEX
    Explanations

    code, data, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    どうぞ
    0.50
     Мор
    0.47
     принадлежа
    0.46
     잘못
    0.46
     βρίσκεται
    0.45
     余
    0.44
     Затем
    0.44
     குறிப்பிடத்தக்க
    0.44
    āli
    0.43
    μέν
    0.43
    POSITIVE LOGITS
     visant
    0.43
    yssey
    0.42
     replaces
    0.41
    বসাইট
    0.40
    िकुलर
    0.40
     noe
    0.40
    چھا
    0.39
     eth
    0.39
     metaphys
    0.39
    വു
    0.39
    Act Density 0.000%

    No Known Activations