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

    Neuronpedia

    INDEX
    Explanations

    notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     키
    -0.06
    -girl
    -0.06
     два
    -0.06
     Ig
    -0.06
    _png
    -0.06
    elim
    -0.06
    php
    -0.06
    ({"
    -0.06
     прем
    -0.06
     прям
    -0.06
    POSITIVE LOGITS
     notation
    0.08
     shorthand
    0.07
    thumbnail
    0.07
     hashing
    0.07
     status
    0.06
    Payment
    0.06
     رسم
    0.06
    Commercial
    0.06
     slab
    0.06
     paperwork
    0.06
    Act Density 0.004%

    No Known Activations