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

    Neuronpedia

    INDEX
    Explanations

    Library

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دي
    -0.08
     cuir
    -0.07
     каб
    -0.07
     satin
    -0.07
     famili
    -0.07
     eth
    -0.07
     confusing
    -0.07
     ضغط
    -0.07
     perform
    -0.07
     directions
    -0.07
    POSITIVE LOGITS
     Margaret
    0.09
    ’Ar
    0.09
     ope
    0.08
     Tru
    0.08
     свидетель
    0.08
     ব্যবস্থা
    0.08
     Michelle
    0.07
     públicas
    0.07
     lyn
    0.07
    版权
    0.07
    Act Density 0.011%

    No Known Activations