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

    Neuronpedia

    INDEX
    Explanations

    digital twin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dresser
    -0.08
     bubb
    -0.08
    ombre
    -0.08
     pec
    -0.08
    Suppress
    -0.08
    alida
    -0.08
     deductible
    -0.07
     tetr
    -0.07
    ক্ষেপ
    -0.07
     getopt
    -0.07
    POSITIVE LOGITS
    จริง
    0.08
     Technology
    0.08
    .boolean
    0.08
     प्रण
    0.08
     구축
    0.07
     Бога
    0.07
     tích
    0.07
     �
    0.07
     վ
    0.07
     technology
    0.07
    Act Density 0.001%

    No Known Activations