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

    Neuronpedia

    INDEX
    Explanations

    phrases that assert statements about truth or reality

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

    the reality is that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.62
     Normdatei
    -0.60
     beginnetje
    -0.59
    SharedCtor
    -0.59
    pædia
    -0.57
     ſind
    -0.56
     ویکی‌پدی
    -0.55
    verwijspagina
    -0.54
     препратки
    -0.53
    FieldBuilder
    -0.52
    POSITIVE LOGITS
     reality
    0.87
     truth
    0.84
    Reality
    0.82
     realidad
    0.77
     Reality
    0.76
    reality
    0.75
    Truth
    0.74
     Truth
    0.74
     réalité
    0.74
     realidade
    0.70
    Act Density 0.013%

    No Known Activations