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

    Neuronpedia

    INDEX
    Explanations

    references to introspection or self-reflection in relation to perception

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

    "mirror" and its synonyms

    np_acts-logits-general · gemini-2.0-flash

    mirror and reflection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.51
    canakan
    -0.51
    pushFollow
    -0.48
     wireType
    -0.42
     محفوظة
    -0.40
     Layton
    -0.40
     aportar
    -0.40
     @"/
    -0.39
    disposing
    -0.38
     PublicKey
    -0.38
    POSITIVE LOGITS
     mirror
    2.58
     reflection
    2.37
     mirrors
    2.28
     Mirror
    2.17
    mirror
    2.15
    Mirror
    2.11
     Mirrors
    2.05
     reflections
    2.03
     MIRROR
    2.02
     Reflection
    1.99
    Act Density 0.129%

    No Known Activations