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

    Neuronpedia

    INDEX
    Explanations

    musical movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     имеются
    0.62
    cognitive
    0.57
    f
    0.54
    helium
    0.53
     имеется
    0.53
    frying
    0.52
     эффективность
    0.52
    WA
    0.50
    biological
    0.50
    डब्ल्यू
    0.50
    POSITIVE LOGITS
    és
    0.59
    uß
    0.52
     يق
    0.52
     ಮನೆಯ
    0.52
    omba
    0.50
     ба
    0.50
    inien
    0.49
     viên
    0.49
    ában
    0.48
    ()},
    0.48
    Act Density 0.001%

    No Known Activations