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

    Neuronpedia

    INDEX
    Explanations

    Decomposition and reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hue
    -0.07
    Hey
    -0.06
    '}).
    -0.06
     yen
    -0.06
     시
    -0.06
    (rec
    -0.06
    (N
    -0.06
    立刻
    -0.06
    /K
    -0.06
     bribery
    -0.06
    POSITIVE LOGITS
    ernity
    0.06
    -analysis
    0.06
    caled
    0.06
    faces
    0.06
     NoSuch
    0.06
    ject
    0.06
    инов
    0.06
    ogne
    0.06
     дослідження
    0.06
     deton
    0.06
    Act Density 0.035%

    No Known Activations