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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the quality and effectiveness of outcomes

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

    better results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ništ
    -0.51
     <<<<<<<<<<<<<<
    -0.47
     PopupWindow
    -0.44
    Personensuche
    -0.41
    mocks
    -0.39
    出版年
    -0.39
     nahilalakip
    -0.39
    bose
    -0.39
     <=",
    -0.38
    NameInMap
    -0.38
    POSITIVE LOGITS
     results
    0.69
     resultaten
    0.65
     resultados
    0.62
    results
    0.59
     efficacité
    0.58
     rezult
    0.57
     résultats
    0.56
     resultat
    0.56
    效果
    0.54
     erzielen
    0.54
    Act Density 0.032%

    No Known Activations