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

    Neuronpedia

    INDEX
    Explanations

    't

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jelly
    -0.07
     VF
    -0.07
     undecided
    -0.07
    came
    -0.07
    VI
    -0.07
    陷
    -0.07
    ürn
    -0.07
    落在
    -0.07
    	cr
    -0.07
    硬
    -0.07
    POSITIVE LOGITS
    价格上涨
    0.08
    伊斯
    0.07
     Darkness
    0.07
    blings
    0.07
     nums
    0.07
     systemFontOfSize
    0.07
    (accounts
    0.07
     ).↵↵
    0.07
    数组
    0.07
    dued
    0.07
    Act Density 0.030%

    No Known Activations