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

    Neuronpedia

    INDEX
    Explanations

    communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alet
    -0.06
     Tire
    -0.06
    otas
    -0.06
     synced
    -0.06
    체
    -0.06
    paragraph
    -0.06
     block
    -0.06
     CI
    -0.06
     sĩ
    -0.06
    ^^
    -0.06
    POSITIVE LOGITS
    　　　　　　　　　　　　　　　
    0.07
     asiat
    0.06
     quartz
    0.06
     adrenal
    0.06
    ,true
    0.06
    協
    0.06
     رسم
    0.06
     умер
    0.06
     MSNBC
    0.06
     xã
    0.06
    Act Density 0.018%

    No Known Activations