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

    Neuronpedia

    INDEX
    Explanations

    Code errors and debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ాం�
    -0.08
     Chancen
    -0.07
     margins
    -0.07
     प्रय
    -0.07
    تهي
    -0.07
     unsere
    -0.07
     ét
    -0.07
     Sai
    -0.07
     ERP
    -0.07
     margen
    -0.07
    POSITIVE LOGITS
     来源
    0.13
     originating
    0.12
     originate
    0.11
    出处
    0.11
     originated
    0.10
     어디
    0.10
    是谁
    0.10
     originates
    0.10
    来源
    0.10
     Duplicate
    0.09
    Act Density 0.006%

    No Known Activations