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

    Neuronpedia

    INDEX
    Explanations

    key insights and observations related to truth and understanding in various contexts

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

    truths and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.67
     Reſ
    -0.62
    featureID
    -0.62
     ſte
    -0.60
     ſind
    -0.59
     juſ
    -0.59
     houſe
    -0.58
     ſta
    -0.57
     ब्रेकडाउन
    -0.57
    Personensuche
    -0.56
    POSITIVE LOGITS
     truths
    0.52
    richTextPanel
    0.51
     Erkenntnis
    0.47
     facts
    0.45
     Erkenntnisse
    0.43
     verdades
    0.41
     fact
    0.41
    CONCLUSIONES
    0.40
     Truths
    0.40
     conclusión
    0.39
    Act Density 0.112%

    No Known Activations