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

    Neuronpedia

    INDEX
    Explanations

    linguistic features and structures specific to the Trúmá language

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

    Language, linguistics, or grammar

    np_acts-logits-general · gemini-2.0-flash

    languages and linguistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.64
    VersionUID
    -0.61
    AntiForgeryToken
    -0.60
     événement
    -0.58
     DBNull
    -0.57
    TargetException
    -0.56
    __*/
    -0.53
    CloseOperation
    -0.53
     prévention
    -0.50
     évé
    -0.50
    POSITIVE LOGITS
     lingu
    0.90
     linguistic
    0.89
     linguistics
    0.89
     gramm
    0.88
     Linguistics
    0.84
     Lingu
    0.80
     linguistique
    0.80
     Chomsky
    0.80
     languages
    0.78
     Languages
    0.77
    Act Density 0.494%

    No Known Activations