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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lightweight
    -0.08
     moderately
    -0.08
     sleepy
    -0.07
     sø
    -0.07
    onal
    -0.07
    委会
    -0.07
     chemotherapy
    -0.07
    /train
    -0.07
     mild
    -0.07
    雾
    -0.07
    POSITIVE LOGITS
     enthusi
    0.08
     obe
    0.08
    OWNER
    0.07
    (iterator
    0.07
     أد
    0.07
    grab
    0.07
    (files
    0.07
     chai
    0.06
    Խ
    0.06
    индив
    0.06
    Act Density 0.015%

    No Known Activations