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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    foreign words and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.59
    RegressionTest
    -0.56
     виправивши
    -0.52
    WritableDatabase
    -0.52
    listdir
    -0.52
    GTCX
    -0.52
    GEBURTS
    -0.46
    GraphicsUnit
    -0.44
     ویکی‌پدی
    -0.44
    IVEREF
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.46
     EconPapers
    0.40
     elettrica
    0.39
     QtWidgets
    0.38
    ябре
    0.36
     attiva
    0.35
     trecut
    0.35
    AnchorStyles
    0.35
    ंदीखरीदारी
    0.34
     arquitectura
    0.34
    Act Density 0.005%

    No Known Activations