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

    Neuronpedia

    INDEX
    Explanations

    29

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {o
    -0.08
     sight
    -0.07
     nối
    -0.07
    pressed
    -0.07
     Dense
    -0.07
     bottle
    -0.07
     nose
    -0.07
     desperation
    -0.07
     bottoms
    -0.07
     tongues
    -0.07
    POSITIVE LOGITS
     hrá
    0.06
    рим
    0.06
     مناطق
    0.06
    Brandon
    0.06
     ）
    0.06
    蒙
    0.06
    NR
    0.06
    .Mon
    0.06
     �
    0.06
    /am
    0.06
    Act Density 0.051%

    No Known Activations