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

    Neuronpedia

    INDEX
    Explanations

    Java-related error messages and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Japanese code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verteilung
    -0.49
    sstil
    -0.48
     vétérina
    -0.47
    련
    -0.47
    ianum
    -0.43
    forhold
    -0.43
    룡
    -0.43
    eclamp
    -0.43
     Erziehung
    -0.42
    verkehr
    -0.42
    POSITIVE LOGITS
    RetentionPolicy
    0.94
    providedIn
    0.84
    Hauptartikel
    0.84
    parsedMessage
    0.82
    .*")]
    0.81
    出版年
    0.78
    ⋙
    0.75
    enumii
    0.73
    UserScript
    0.73
    RegressionTest
    0.72
    Act Density 6.179%

    No Known Activations