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

    Neuronpedia

    INDEX
    Explanations

    Random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Як
    -0.07
    Were
    -0.07
     classical
    -0.07
    ασίας
    -0.06
    559
    -0.06
    古
    -0.06
    183
    -0.06
     Nim
    -0.06
     sales
    -0.06
    acho
    -0.06
    POSITIVE LOGITS
    (directory
    0.07
    olist
    0.07
    �인
    0.06
     Inspiration
    0.06
    监
    0.06
    .Program
    0.06
    	 
↵
    0.06
     ngOnDestroy
    0.06
     Truy
    0.06
     पड़
    0.06
    Act Density 0.004%

    No Known Activations