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

    Neuronpedia

    INDEX
    Explanations

    various

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🤐
    -0.08
    明知
    -0.07
    Tester
    -0.07
    뜻
    -0.07
    indsay
    -0.06
    קל
    -0.06
     linking
    -0.06
    _pri
    -0.06
     aroma
    -0.06
    $',
    -0.06
    POSITIVE LOGITS
    (frames
    0.07
           
    0.07
     초
    0.07
     discontin
    0.07
     Citizens
    0.06
     Articles
    0.06
    }`);↵↵
    0.06
    叙事
    0.06
    halb
    0.06
    �습니다
    0.06
    Act Density 0.019%

    No Known Activations