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

    Neuronpedia

    INDEX
    Explanations

    Text tagging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     правило
    -0.06
     fragment
    -0.06
    هه
    -0.06
    들도
    -0.06
    estar
    -0.06
     difer
    -0.06
    package
    -0.06
     vibrant
    -0.06
     explained
    -0.06
    이었다
    -0.06
    POSITIVE LOGITS
     apa
    0.08
    활동
    0.07
     Atlas
    0.06
    iệu
    0.06
    -ts
    0.06
     individuals
    0.06
    /api
    0.06
    153
    0.06
     depressive
    0.06
     flip
    0.06
    Act Density 0.028%

    No Known Activations