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

    Neuronpedia

    INDEX
    Explanations

    dumplings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    0.82
    ي
    0.66
    心
    0.66
    Р
    0.65
    ا
    0.62
    أي
    0.60
    ير
    0.59
    க்கு
    0.58
    ल्ल्या
    0.58
    ﻳ
    0.58
    POSITIVE LOGITS
     dumplings
    0.81
    🥟
    0.64
     dumpling
    0.61
    AN
    0.60
     shears
    0.60
    ()),
    0.60
    opak
    0.60
    /',
    0.59
    bullets
    0.58
     wcout
    0.58
    Act Density 0.004%

    No Known Activations