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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and conjunctions within the text

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

    sentence beginnings after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jard
    -0.48
     matchup
    -0.48
     vastly
    -0.47
     comedic
    -0.47
     marketplace
    -0.47
     smarter
    -0.46
     unwit
    -0.46
     tiered
    -0.45
    fahr
    -0.44
     NYC
    -0.44
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    ChildScrollView
    0.49
    awtextra
    0.48
     cherchés
    0.48
     rospy
    0.47
     للاسماء
    0.47
    contentValues
    0.47
     gesloten
    0.43
    getMenuInflater
    0.43
    PasswordEncoder
    0.42
    Act Density 0.111%

    No Known Activations