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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /lg
    -0.07
    	damage
    -0.06
    raya
    -0.06
     textbook
    -0.06
     dikkate
    -0.06
     Gunn
    -0.06
     with
    -0.06
     cartoons
    -0.06
     By
    -0.06
    нити
    -0.06
    POSITIVE LOGITS
    许多
    0.08
    722
    0.07
     경찰
    0.06
    （笑
    0.06
    ilen
    0.06
     arasındaki
    0.06
    *******/↵
    0.06
    $GLOBALS
    0.06
     milyar
    0.06
    레스
    0.06
    Act Density 0.033%

    No Known Activations