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

    Neuronpedia

    INDEX
    Explanations

    capturing long-range dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     into
    0.48
    into
    0.38
    ez
    0.38
     vào
    0.37
     returned
    0.37
     Into
    0.36
     off
    0.36
     relating
    0.36
     my
    0.36
     start
    0.36
    POSITIVE LOGITS
    ласти
    0.42
    䒿
    0.41
    льность
    0.40
    र्दशी
    0.40
    вол
    0.39
    ড়াতে
    0.39
    ثر
    0.38
     نگرانی
    0.38
    assistance
    0.38
    entingan
    0.38
    Act Density 0.000%

    No Known Activations