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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific individuals or titles in a narrative

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

    Mongolian context or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.36
    fromUtf
    -0.31
    CDCl
    -0.30
    frau
    -0.28
    eningen
    -0.28
    FXML
    -0.28
     défense
    -0.28
     lengu
    -0.27
     navideño
    -0.27
     jupe
    -0.27
    POSITIVE LOGITS
     Mongolia
    0.85
     '\\;'
    0.65
    Хьажоргаш
    0.61
     pymongo
    0.61
     Mongolian
    0.60
     Roskov
    0.59
    meteor
    0.59
    UnusedPrivate
    0.58
    蒙古
    0.57
    RegressionTest
    0.56
    Act Density 0.017%

    No Known Activations