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

    Neuronpedia

    INDEX
    Explanations

    linguistic terminology and concepts related to syntax

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

    word order and placement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pausal
    -0.38
     penna
    -0.38
    ulitis
    -0.37
     Unicode
    -0.37
     Сим
    -0.36
     tex
    -0.36
    glyph
    -0.35
    asymp
    -0.35
    script
    -0.35
    sich
    -0.34
    POSITIVE LOGITS
    SourceChecksum
    0.65
     desmotivaciones
    0.64
     estekak
    0.60
    AndEndTag
    0.57
     miniaturka
    0.54
    0.52
     revanche
    0.49
     Rückkehr
    0.49
     للاسماء
    0.49
     Normdatei
    0.48
    Act Density 0.146%

    No Known Activations