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

    Neuronpedia

    INDEX
    Explanations

    parenthesis and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	D
    -0.07
     Che
    -0.07
     ie
    -0.07
    дивиду
    -0.07
    œ
    -0.06
     tasarım
    -0.06
    凡
    -0.06
     indign
    -0.06
    electronics
    -0.06
    '};↵
    -0.06
    POSITIVE LOGITS
    합니다
    0.06
    ΟΣ
    0.06
    mıştır
    0.06
    兽
    0.06
    .CreateCommand
    0.06
    ASA
    0.06
    LOY
    0.06
     olmuştur
    0.06
    allet
    0.06
    봐
    0.06
    Act Density 0.040%

    No Known Activations