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

    Neuronpedia

    INDEX
    Explanations

    events following possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eines
    0.70
    Ⲏ
    0.65
     നിന്നും
    0.64
     YEARS
    0.61
    𒅗
    0.61
     Lyapunov
    0.60
     einer
    0.60
     CMake
    0.59
     codons
    0.59
    শতঃ
    0.58
    POSITIVE LOGITS
     محد
    0.54
    0.54
     latter
    0.52
    cl
    0.52
    ne
    0.52
    book
    0.47
    big
    0.47
    rock
    0.46
    b
    0.46
    be
    0.45
    Act Density 0.003%

    No Known Activations