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

    Neuronpedia

    INDEX
    Explanations

    references to linguistic features or studies

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

    linguistics and language grammar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }{@
    -0.52
     للاسماء
    -0.44
    findpost
    -0.43
     onCreateView
    -0.41
    期刊论文
    -0.41
    verwijspagina
    -0.39
    glades
    -0.39
    rawDesc
    -0.38
     Gland
    -0.38
     figur
    -0.38
    POSITIVE LOGITS
     linguistics
    0.58
     Linguistics
    0.57
     invokingState
    0.54
     linguistique
    0.52
    linguistic
    0.50
     linguistic
    0.50
     lingü
    0.42
     Linguistic
    0.42
    Lingu
    0.41
    twimg
    0.40
    Act Density 0.036%

    No Known Activations