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

    Neuronpedia

    INDEX
    Explanations

    references to physical confrontations and struggles

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

    physical actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Modo
    -0.34
     expose
    -0.32
    冒
    -0.32
    粒
    -0.31
     demand
    -0.30
    expose
    -0.30
     django
    -0.30
    жд
    -0.29
    hôte
    -0.29
    超
    -0.29
    POSITIVE LOGITS
    Personendaten
    0.72
     nakalista
    0.72
     disambiguazione
    0.70
    الحياه
    0.66
     يتيمه
    0.61
    Hentet
    0.60
     ویکی‌پدی
    0.58
    tanleria
    0.56
     beginnetje
    0.54
    Παραπομπές
    0.52
    Act Density 0.039%

    No Known Activations