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

    Neuronpedia

    INDEX
    Explanations

    references to personal connections and relationships

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

    address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.73
    ंदीखरीदारी
    -0.72
    verwijspagina
    -0.66
     Normdatei
    -0.62
    rungsseite
    -0.62
    majánló
    -0.57
    󠁢
    -0.56
     الدولى
    -0.55
    ྛ
    -0.54
     تضيفلها
    -0.53
    POSITIVE LOGITS
     mon
    0.39
    Tja
    0.38
     directly
    0.37
     otherwise
    0.34
     essentially
    0.33
     multiple
    0.32
    AppRoutingModule
    0.32
     dica
    0.31
     actually
    0.31
    存知
    0.31
    Act Density 0.040%

    No Known Activations