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

    Neuronpedia

    INDEX
    Explanations

    bar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Savior
    -0.07
     primero
    -0.07
     Potter
    -0.06
    '.↵↵
    -0.06
    ULK
    -0.06
    出版
    -0.06
     stint
    -0.06
    更多
    -0.06
     Hồng
    -0.06
     Hermione
    -0.06
    POSITIVE LOGITS
    \application
    0.07
    شهر
    0.07
     assertTrue
    0.07
    _transfer
    0.07
     katıl
    0.07
    	assertTrue
    0.06
     sewing
    0.06
     ##↵
    0.06
     výsledky
    0.06
     gute
    0.06
    Act Density 0.000%

    No Known Activations