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

    Neuronpedia

    INDEX
    Explanations

    categories or classifications of entities

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

    Category names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alfombra
    -0.45
     TAMBÉM
    -0.42
     Wikiseite
    -0.40
     Italijani
    -0.39
     nemlig
    -0.39
    Personendaten
    -0.39
     hendes
    -0.39
     efectivamente
    -0.38
     peligros
    -0.37
     peligroso
    -0.36
    POSITIVE LOGITS
     [*]
    0.63
    })));
    0.61
     queſto
    0.59
    ंदीखरीदारी
    0.57
    ╽
    0.57
     Vul
    0.55
    ]}>
    0.54
    giver
    0.54
     Avalon
    0.54
    copal
    0.54
    Act Density 0.053%

    No Known Activations