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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voorstellen
    -0.08
     عهد
    -0.08
     Prisma
    -0.08
     sarà
    -0.07
     Και
    -0.07
     Eka
    -0.07
     ressembl
    -0.07
     Екат
    -0.07
    otiv
    -0.07
     aposta
    -0.07
    POSITIVE LOGITS
    .STATE
    0.08
     debugging
    0.08
     ship
    0.08
     gathering
    0.08
    .prepare
    0.08
     обучения
    0.07
     breakthroughs
    0.07
     Bry
    0.07
    _SECTION
    0.07
     gbig
    0.07
    Act Density 0.002%

    No Known Activations