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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     einz
    -0.06
     ож
    -0.06
    /I
    -0.06
     obr
    -0.06
     corridor
    -0.06
    ű
    -0.06
    (validate
    -0.06
     postcode
    -0.06
    ฤ
    -0.05
    -lines
    -0.05
    POSITIVE LOGITS
     Blast
    0.07
    Muslim
    0.07
    xE
    0.06
    access
    0.06
     Savaş
    0.06
    038
    0.06
     Luk
    0.06
    incess
    0.06
     มหาว
    0.06
    xC
    0.06
    Act Density 0.015%

    No Known Activations