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

    Neuronpedia

    INDEX
    Explanations

    implicitly, gateway, viewport, every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.68
    4
    0.54
     bumpers
    0.52
    soft
    0.51
    3
    0.51
     nipples
    0.50
     दुर्गेश
    0.50
     المياه
    0.48
     tampon
    0.48
    មី
    0.48
    POSITIVE LOGITS
     inl
    0.47
     배열
    0.46
    ाइब
    0.44
     불구하고
    0.43
    اين
    0.41
     parecido
    0.41
    찬가지
    0.41
    ებულია
    0.41
    ườ
    0.40
     resemblance
    0.40
    Act Density 0.001%

    No Known Activations