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

    Neuronpedia

    INDEX
    Explanations

    Baker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     truy
    -0.07
    !!!!
    -0.06
    няя
    -0.06
     Directive
    -0.06
    ylon
    -0.06
     ноги
    -0.06
    ^^^^
    -0.06
     различ
    -0.06
    Ny
    -0.06
    ňují
    -0.06
    POSITIVE LOGITS
     Baker
    0.10
    aker
    0.10
    AKER
    0.09
     baker
    0.07
     agent
    0.07
    eties
    0.07
    евер
    0.07
     Ak
    0.07
    emaker
    0.07
    ámara
    0.07
    Act Density 0.004%

    No Known Activations