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

    Neuronpedia

    INDEX
    Explanations

    Middleware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌خ
    -0.07
     McG
    -0.07
     LENG
    -0.06
    �
    -0.06
    १�
    -0.06
     -------------------------------------------------------------------------↵
    -0.06
     LeBron
    -0.06
    ects
    -0.06
     Strand
    -0.06
     SCN
    -0.06
    POSITIVE LOGITS
     middleware
    0.07
     funding
    0.06
     wrongful
    0.06
    Through
    0.06
    ряду
    0.06
    quate
    0.06
    \Middleware
    0.06
    념
    0.06
     niệm
    0.06
     supplement
    0.06
    Act Density 0.002%

    No Known Activations