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

    Neuronpedia

    INDEX
    Explanations

    phrases related to language proficiency and multilingualism

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

    Fluency or proficiency in a language

    np_acts-logits-general · gemini-2.0-flash

    language fluency proficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.53
    lieferung
    -0.51
     UnityEditor
    -0.50
    titur
    -0.48
     humaine
    -0.46
    TokenName
    -0.43
    stdc
    -0.42
     prevenção
    -0.42
     sièges
    -0.42
    ември
    -0.41
    POSITIVE LOGITS
     proficiency
    1.30
     fluent
    1.13
     proficient
    1.09
     Proficiency
    1.09
     mastered
    1.05
     learning
    1.05
     mastering
    1.05
     fluency
    1.03
     mastery
    1.00
     Mastering
    1.00
    Act Density 0.179%

    No Known Activations