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

    Neuronpedia

    INDEX
    Explanations

    equation, energy, boundary conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     empresario
    0.47
    ப்போ
    0.45
    اداس
    0.43
    线的
    0.40
     telo
    0.40
    大佬
    0.40
    平
    0.40
     demostrar
    0.39
     দিয়েছে
    0.39
    க்கிய
    0.39
    POSITIVE LOGITS
    そこで
    0.43
     \
    0.39
     User
    0.39
    ༽
    0.39
     Inflammation
    0.38
    heiz
    0.38
     qual
    0.37
     gì
    0.37
    striction
    0.37
    avat
    0.36
    Act Density 0.001%

    No Known Activations