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

    Neuronpedia

    INDEX
    Explanations

    on/of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赫
    -0.06
    .inject
    -0.06
     cộng
    -0.06
     상세
    -0.06
    かし
    -0.06
     Ale
    -0.06
     защит
    -0.06
     Sof
    -0.06
     bn
    -0.06
    ปกครอง
    -0.06
    POSITIVE LOGITS
    rolls
    0.08
    events
    0.07
    yst
    0.07
     position
    0.07
     positions
    0.07
     replace
    0.07
     upset
    0.06
    slashes
    0.06
    usses
    0.06
    .ToInt
    0.06
    Act Density 0.026%

    No Known Activations