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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss changes, conditions, or transitions related to systems or processes

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

    either or, in fact, to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ambién
    -0.45
     pleaſure
    -0.45
     marbre
    -0.45
     <>",
    -0.42
     brisa
    -0.42
    SBATCH
    -0.41
     Seigneur
    -0.40
     fondateur
    -0.40
    Istorija
    -0.40
    XmlAccessType
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.55
    лтемелер
    0.54
    httphttps
    0.52
    rungsseite
    0.50
    SharedDtor
    0.47
    writeField
    0.45
    cline
    0.44
     ligiloj
    0.42
    liferay
    0.42
    TagMode
    0.41
    Act Density 0.047%

    No Known Activations