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

    Neuronpedia

    INDEX
    Explanations

    linguistic origins and meanings of words from various languages

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

    languages and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.98
     виправивши
    -0.89
     utafitiHapana
    -0.89
     Roskov
    -0.87
    expandindo
    -0.84
    Personensuche
    -0.82
     ujednoznacz
    -0.80
    ThroughAttribute
    -0.79
    ContentAlignment
    -0.77
    Diwedd
    -0.76
    POSITIVE LOGITS
     words
    0.73
     word
    0.73
     phrase
    0.59
     meaning
    0.58
     term
    0.56
     language
    0.53
     name
    0.52
     terms
    0.48
     meanings
    0.44
     "
    0.43
    Act Density 0.023%

    No Known Activations