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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dead
    -0.07
     đăng
    -0.07
     напрям
    -0.06
    ility
    -0.06
    .eval
    -0.06
     Dead
    -0.06
     UIViewController
    -0.06
     Михай
    -0.06
     так
    -0.06
    _phys
    -0.06
    POSITIVE LOGITS
     combining
    0.08
     combines
    0.07
    py
    0.06
    playing
    0.06
    Debugger
    0.06
    )
↵
↵
    0.06
    pent
    0.06
     combine
    0.06
     capitalize
    0.06
     objectMapper
    0.06
    Act Density 0.012%

    No Known Activations