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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strncmp
    -0.07
     вер
    -0.07
     INIT
    -0.06
    áním
    -0.06
     STR
    -0.06
     PG
    -0.06
     villains
    -0.06
     uniqu
    -0.06
    MenuItem
    -0.06
     pi
    -0.06
    POSITIVE LOGITS
    (cursor
    0.07
    _COOKIE
    0.07
    arranty
    0.07
     electronic
    0.06
     lãnh
    0.06
     Topics
    0.06
    		  ↵
    0.06
    (
↵
    0.06
    �
    0.06
     Caucus
    0.06
    Act Density 0.073%

    No Known Activations