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

    Neuronpedia

    INDEX
    Explanations

    cultural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ನಮ್ಮ
    -0.09
     unseres
    -0.09
    aut
    -0.09
    Aut
    -0.08
     שלנו
    -0.08
     bijvoorbeeld
    -0.08
     ಶಾಸ
    -0.08
     આપણા
    -0.08
     আমাদের
    -0.08
     например
    -0.08
    POSITIVE LOGITS
    .Ad
    0.08
    sis
    0.07
     넘어
    0.07
     dump
    0.07
    verted
    0.07
     finales
    0.07
     exchange
    0.07
     rapidly
    0.07
     relentless
    0.07
    .Buffer
    0.07
    Act Density 2.814%

    No Known Activations