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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rians
    -0.08
    衛
    -0.07
    usters
    -0.07
     somewhere
    -0.07
     bouncing
    -0.07
    мовір
    -0.07
     leans
    -0.07
    -ever
    -0.07
    ัมพ
    -0.07
     قهر
    -0.07
    POSITIVE LOGITS
    骨
    0.08
    _inventory
    0.07
     [-
    0.06
     лит
    0.06
    GetData
    0.06
      
    0.06
     misled
    0.06
    InBackground
    0.06
    indx
    0.06
     ذ
    0.06
    Act Density 0.014%

    No Known Activations