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

    Neuronpedia

    INDEX
    Explanations

    programming constructs in code snippets

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

    ending and conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DIPSETTING
    -0.71
    TagMode
    -0.68
     Савезне
    -0.68
    SequentialGroup
    -0.65
    NameInMap
    -0.63
    */),
    -0.63
     autorytatywna
    -0.62
     propOrder
    -0.62
     Мексичка
    -0.61
    Cyfarwyddwr
    -0.60
    POSITIVE LOGITS
     concluding
    0.50
     last
    0.49
     pungkasnya
    0.45
     últimos
    0.44
     final
    0.42
     dernier
    0.41
     última
    0.41
     conclude
    0.41
     dernières
    0.40
    <eos>
    0.40
    Act Density 0.006%

    No Known Activations