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

    Neuronpedia

    INDEX
    Explanations

    education and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.47
     relegation
    0.46
    bol
    0.46
    bor
    0.45
     infliction
    0.43
     meaty
    0.43
    razione
    0.42
    zeichnis
    0.42
     protrusion
    0.42
    haan
    0.42
    POSITIVE LOGITS
     విద్య
    0.54
     животных
    0.53
     Моло
    0.49
     তাদের
    0.49
     त्यांनी
    0.47
     আজ
    0.46
    дук
    0.46
     తయారు
    0.46
    菓子
    0.46
     Нау
    0.46
    Act Density 0.006%

    No Known Activations