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

    Neuronpedia

    INDEX
    Explanations

    rugs and skins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.48
    de
    0.46
    l
    0.46
    ate
    0.45
    dy
    0.45
    gel
    0.45
    ru
    0.43
    ang
    0.42
    uer
    0.41
    resa
    0.41
    POSITIVE LOGITS
     кафед
    0.42
    ک
    0.39
     ಸದಸ್ಯ
    0.39
    ی
    0.36
     interação
    0.36
    യായി
    0.36
    ﻜ
    0.36
     Alhaji
    0.35
     giấy
    0.35
     эксперимента
    0.34
    Act Density 0.001%

    No Known Activations