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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations and descriptions of quality or attributes

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

    positive evaluation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.54
     gewel
    -0.42
     culturelle
    -0.41
    TypedDataSet
    -0.40
     spécialisée
    -0.39
     mijne
    -0.39
     Fah
    -0.36
    🤯
    -0.36
     phénom
    -0.36
     koniecz
    -0.36
    POSITIVE LOGITS
     للمعارف
    0.70
     abbastanza
    0.62
     decent
    0.59
     nicely
    0.57
     непло
    0.56
    Decent
    0.56
     astore
    0.54
     decently
    0.54
     agreeable
    0.54
     Decent
    0.54
    Act Density 0.186%

    No Known Activations