INDEX
    Explanations

    This neuron detects mentions of the Nintendo Switch (and related Nintendo console names) in the text.

    New Auto-Interp
    Negative Logits
     повин
    -0.08
     програ
    -0.07
    /features
    -0.06
    оян
    -0.06
    ported
    -0.06
    práv
    -0.06
    /Users
    -0.06
     spinning
    -0.06
    .St
    -0.06
    Chars
    -0.06
    POSITIVE LOGITS
     commencement
    0.07
     dB
    0.07
     буду
    0.07
    >
    ↵
    ↵
    ↵
    0.07
     Switch
    0.07
     thuận
    0.07
    vx
    0.07
     Spain
    0.07
    _SECONDS
    0.06
     specialties
    0.06
    Act Density 0.001%

    No Known Activations