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

    Neuronpedia

    INDEX
    Explanations

    references to various types of interfaces

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

    interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })),
    -0.44
    stagland
    -0.40
     Nuestros
    -0.40
    Adverten
    -0.39
    ())))
    -0.39
    ])))
    -0.39
     Wyn
    -0.39
    getP
    -0.39
    ()")
    -0.38
     Poy
    -0.38
    POSITIVE LOGITS
     interface
    1.87
     interfaces
    1.62
    interface
    1.53
     Interface
    1.48
     INTERFACE
    1.47
     Interfaces
    1.35
     interfaz
    1.23
     интерфей
    1.15
    INTERFACE
    1.09
    接口
    1.09
    Act Density 0.007%

    No Known Activations