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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and phrases indicating speech

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

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.31
     weiteren
    -0.30
     apart
    -0.29
     run
    -0.29
    menden
    -0.28
    _()
    -0.28
     perdu
    -0.28
     Süden
    -0.28
     tedy
    -0.28
    ?>
    -0.28
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.78
    AndEndTag
    0.77
     فريبيس
    0.71
    awtextra
    0.70
     defaultstate
    0.70
    AccessorTable
    0.70
     CreateTagHelper
    0.69
    UrlResolution
    0.68
    Personensuche
    0.66
     صوتيه
    0.66
    Act Density 0.023%

    No Known Activations