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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual relevance in sentences

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

    final words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBOutlet
    -0.61
    Bibliograf
    -0.58
     IBOutlet
    -0.52
    mybatisplus
    -0.52
     Италијани
    -0.51
     disambiguazione
    -0.50
     pinulongan
    -0.50
     JpaRepository
    -0.49
     poveznice
    -0.48
    graphique
    -0.47
    POSITIVE LOGITS
     Finally
    0.41
    最终
    0.38
     finally
    0.37
    CppMethod
    0.37
    Finally
    0.37
    impresa
    0.35
    पया
    0.35
    Finish
    0.35
     mér
    0.34
    final
    0.33
    Act Density 0.043%

    No Known Activations