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

    Neuronpedia

    INDEX
    Explanations

    blogging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cutting
    -0.07
     инструмент
    -0.06
     rece
    -0.06
    '],
    -0.06
     price
    -0.06
     dp
    -0.06
     PRICE
    -0.06
     quali
    -0.06
     Price
    -0.06
     greed
    -0.06
    POSITIVE LOGITS
    aphore
    0.07
     žád
    0.06
    owners
    0.06
     жил
    0.06
    قی
    0.06
     Zuckerberg
    0.06
    开发
    0.06
    (requestCode
    0.06
    ΐ
    0.06
     Finger
    0.06
    Act Density 0.004%

    No Known Activations