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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icit
    -0.29
    ict
    -0.28
     intern
    -0.28
    éĢŁ
    -0.28
     t
    -0.27
    设å®ļ
    -0.27
    fore
    -0.27
    atu
    -0.26
     "".
    -0.26
    intern
    -0.26
    POSITIVE LOGITS
    丰满
    0.26
    анÑģ
    0.26
    缸äºĴ
    0.25
    殿
    0.25
    æ¸ļ
    0.25
    æ¹ĸåĮº
    0.25
    峡
    0.24
    å±
    0.24
    äºĴ缸
    0.24
    ersive
    0.24
    Act Density 0.015%

    No Known Activations