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

    Neuronpedia

    INDEX
    Explanations

    words in various contexts and forms

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

    words and their translations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.52
     Clifton
    -0.50
     Gentry
    -0.46
    omaly
    -0.45
    Personensuche
    -0.45
    >(&
    -0.45
    )}{(
    -0.44
     Pesto
    -0.44
    (`/
    -0.44
    ilaire
    -0.44
    POSITIVE LOGITS
     words
    2.05
    Words
    1.91
     Words
    1.88
    words
    1.77
     WORDS
    1.67
     woorden
    1.43
     palabras
    1.42
    WORDS
    1.41
     Worte
    1.30
     palavras
    1.25
    Act Density 0.006%

    No Known Activations