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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folders
    -0.07
     estimate
    -0.07
    ezier
    -0.07
     besteht
    -0.06
     Proposed
    -0.06
     SWT
    -0.06
    Tickets
    -0.06
     UBND
    -0.06
    ились
    -0.06
    pler
    -0.06
    POSITIVE LOGITS
    指数
    0.06
    /mp
    0.06
    peng
    0.06
    зд
    0.06
    ton
    0.06
     terug
    0.06
     hlavně
    0.06
     trả
    0.06
     Eğitim
    0.05
     Milton
    0.05
    Act Density 0.005%

    No Known Activations