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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     checksum
    -0.07
    唯一
    -0.06
    _Model
    -0.06
    -consuming
    -0.06
     vữ
    -0.06
    祖
    -0.06
     Taxes
    -0.06
     potent
    -0.06
     Tax
    -0.06
    _delivery
    -0.06
    POSITIVE LOGITS
     Craigslist
    0.07
     removing
    0.06
     큰
    0.06
    /**
    0.06
     ominous
    0.06
     airs
    0.06
    mong
    0.06
    -ren
    0.06
    -sm
    0.06
     cel
    0.06
    Act Density 0.146%

    No Known Activations