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

    Neuronpedia

    INDEX
    Explanations

    Who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compression
    -0.08
     biomass
    -0.07
    קלאסי
    -0.07
     stylish
    -0.07
     קטן
    -0.06
     Gast
    -0.06
    칸
    -0.06
     disposing
    -0.06
    DAY
    -0.06
    تراجع
    -0.06
    POSITIVE LOGITS
    بدا
    0.09
     обо
    0.08
    	wg
    0.07
    ่วน
    0.07
    一等奖
    0.07
    _seen
    0.07
    졪
    0.07
     optionally
    0.07
    OrCreate
    0.07
    谁都
    0.07
    Act Density 0.021%

    No Known Activations