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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    警察
    -0.06
    875
    -0.06
    έλ
    -0.06
     Вол
    -0.06
    gorm
    -0.06
     wird
    -0.06
     instr
    -0.06
    .uf
    -0.06
     Kur
    -0.06
    增长
    -0.06
    POSITIVE LOGITS
    емати
    0.07
    InBackground
    0.07
    .SetFloat
    0.07
     Moral
    0.07
    ifie
    0.06
    .Disclaimer
    0.06
     payout
    0.06
     besonders
    0.06
    ineTransform
    0.06
    xBE
    0.06
    Act Density 0.001%

    No Known Activations