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

    Neuronpedia

    INDEX
    Explanations

    references to human existence and identity

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

    human being / human existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.52
     సౌకర్య
    -0.49
    KURZBESCHREIBUNG
    -0.49
    ">//
    -0.47
    adaptiveStyles
    -0.46
    rimas
    -0.45
    resulting
    -0.43
    monies
    -0.43
    Futures
    -0.43
    prices
    -0.42
    POSITIVE LOGITS
     eyeballs
    0.39
     humans
    0.39
    tidaknya
    0.36
     ویکی‌پدی
    0.35
    حوالہ
    0.35
    lunda
    0.34
    IntoConstraints
    0.34
     humanidad
    0.33
    édrale
    0.33
    再说
    0.33
    Act Density 0.050%

    No Known Activations