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

    Neuronpedia

    INDEX
    Explanations

    concepts related to innate human abilities and the nature of existence

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

    innate, universal human qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.55
    .*")]
    -0.55
     Administrativna
    -0.52
    RenderAtEndOf
    -0.52
    ftagPool
    -0.51
    NameInMap
    -0.50
    şekkür
    -0.47
    󠁴
    -0.47
    makeConstraints
    -0.47
     Réponses
    -0.45
    POSITIVE LOGITS
     universal
    0.50
     ingrained
    0.41
     humankind
    0.41
     human
    0.40
     everyone
    0.40
     innate
    0.40
    kho
    0.39
     universale
    0.39
     natural
    0.39
     humans
    0.38
    Act Density 0.041%

    No Known Activations