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

    Neuronpedia

    INDEX
    Explanations

    racial demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getAll
    -0.07
     груп
    -0.07
     '::
    -0.07
    changed
    -0.06
    bread
    -0.06
    ivation
    -0.06
    Total
    -0.06
    mates
    -0.06
     Nine
    -0.06
     honest
    -0.06
    POSITIVE LOGITS
    ाड
    0.06
    .anchor
    0.06
    .",
↵
    0.06
     строитель
    0.06
    =id
    0.06
    ınma
    0.06
    (an
    0.06
     düşür
    0.06
     Chess
    0.06
     中国
    0.05
    Act Density 0.007%

    No Known Activations