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

    Neuronpedia

    INDEX
    Explanations

    elements related to decision-making and self-reflection

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

    figuring out what you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mappedBy
    -0.55
    featureID
    -0.51
    SpringBootTest
    -0.46
    ✷
    -0.44
    basicConfig
    -0.42
    ʾ
    -0.42
     européennes
    -0.39
    不幸
    -0.38
     judiciaire
    -0.38
    Indic
    -0.38
    POSITIVE LOGITS
     Exacts
    0.59
     rational
    0.50
     refine
    0.45
     idéia
    0.43
     Réponses
    0.42
     answers
    0.42
     karar
    0.40
     تعدى
    0.40
    tagext
    0.40
     sogni
    0.39
    Act Density 0.016%

    No Known Activations