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

    Neuronpedia

    INDEX
    Explanations

    published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    擔
    -0.07
    Wunused
    -0.07
     eventdata
    -0.07
    (exp
    -0.07
     unnamed
    -0.06
    TIME
    -0.06
    꿰
    -0.06
    �
    -0.06
     Ug
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     learnt
    0.08
    的文章
    0.07
     ease
    0.07
    >|
    0.07
     int
    0.06
    squeeze
    0.06
    ,,,,
    0.06
     conn
    0.06
     author
    0.06
     disclosures
    0.06
    Act Density 0.001%

    No Known Activations