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

    Neuronpedia

    INDEX
    Explanations

    well-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.68
    م
    0.66
    на
    0.61
     время
    0.61
     at
    0.59
    اري
    0.57
     atthe
    0.57
    وری
    0.57
    Gosudarstvennyj
    0.57
     واحدة
    0.56
    POSITIVE LOGITS
    -
    0.77
    ulation
    0.68
    i
    0.61
    {
    0.59
    ulate
    0.57
    '
    0.54
    युक्त
    0.50
    𝐠
    0.50
    uding
    0.49
    ulating
    0.49
    Act Density 0.979%

    No Known Activations