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

    Neuronpedia

    INDEX
    Explanations

    medical, legal, and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.53
    LSTM
    0.49
    op
    0.49
    ীবনী
    0.47
    semble
    0.46
    ed
    0.46
    halla
    0.46
     relacionado
    0.45
     I
    0.45
     সংশ্লিষ্ট
    0.45
    POSITIVE LOGITS
    трон
    0.52
    יום
    0.51
    ی
    0.50
    πτ
    0.49
    （
    0.49
    ０
    0.49
    <0x80>
    0.48
    ﻕ
    0.47
     тобто
    0.46
     parabolic
    0.46
    Act Density 0.128%

    No Known Activations