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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    from
    -0.35
     from
    -0.30
    ä»İ
    -0.29
    à¸Īาà¸ģ
    -0.27
    FROM
    -0.27
    	from
    -0.27
    inder
    -0.26
     từ
    -0.26
    çł´
    -0.26
    #from
    -0.26
    POSITIVE LOGITS
    åĩºåıij
    0.50
    èµ°åĩºæĿ¥
    0.42
     heraus
    0.42
    åĩºä¾Ĩ
    0.38
    åĩºæĿ¥çļĦ
    0.37
    åĩºæĿ¥
    0.35
    åĩºæĿ¥äºĨ
    0.34
    伸åĩº
    0.34
    çľĭåĩº
    0.32
     extraction
    0.31
    Act Density 0.056%

    No Known Activations